Re: OUCB usage
Eric Jackson writes: > For MVS, unlike most other platforms, the terms "swapping" and > "paging" refer to distinct operations. Paging is for a page of memory > in an address space, and swapping is when the entire address space is > swapped out to secondary storage. TSO address spaces waiting for > terminal I/O (for example) will get swapped out so that their memory > resources become available to other address spaces while waiting the > relatively long time for terminal input. > > If you issue a DONTSWAP, paging still continues for your address space. changes i made for cp67 (as undergraudate in the 60s) .. and since the changes were mostly dropped in the simplification in the morph of cp67->vm370 ... re-implemented for vm370 in the 70s ... was pages were individually "paged" ... and at queue drop (for long wait) ... virtual pages might be "collected" ... but nothing actually happened unless there was sufficient demand for pages (aka agile, dynamic adaptive). circa 1980, somebody from the mvs organization contacted me about recent change that had been to MVS, regarding not actually "swapping" pages unless actually needed ... and they wanted to know about making similar change to vm370. I commented, that it had never occured to me to not do it that way ... dating back to when i did the original implementation in the 60s. I actually had earlier arguments with the organization when they were first adding virtual memory to os/360 ... for svs and then mvs. misc. past posts mentioning paging, swapping, page replace algorithms, etc http://www.garlic.com/~lynn/subtopic.html#clock -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: CLOCK change problem
re: http://www.garlic.com/~lynn/2011k.html#27 CLOCK change problem 32bit value with 15hr duration ... different models decrement bits depending on timer resolution of the model. re: http://www.bitsavers.org/pdf/ibm/360/funcChar/GA24-3231-7_360-30_funcChar.pdf pg. 29, Interval Timer The Model 30 Interval Timer (special feature) operates at a fixed cycle rate of 16.7 milliseconds (60-cycle system power-supply input) or 20 milliseconds (50-cycle power). The microprogram controls decrementing the timer The interval-timer microprogram requires 7.5 to 13.5 microseconds (10 to 18 microseconds in a CPU with 2-microsecond RW cycle) per count depending upon whether there is a carry in the count. The cycle occurs asynchronously with respect to the stored program and I/O operation. Backup-up register is provided with the timer feature to accumulate automatically a count of up to 16 intervals of time, if main storage cannot be accessed because of prolonged I/O or direct control operations. The feature permits a delay of up to 277 milliseconds between timer counter references without loss of the count. ... snip ... keeping 16 intervals ... implies that update has to happen before the end of 17th interval ... aka total 277ms divided by 17 intervals is approx. 16ms ... corresponds to the 16.7 milliseconds for 60-cycle power. re: http://www.bitsavers.org/pdf/ibm/360/funcChar/GA27-2719-2_360-67_funcChar.pdf pg. 19 High-Resolution Interval Timer An interval timer with a high degree of resolution is used in 2067. Operation of this timer is fully compatible with that described in the IBM System/360 Principles of Operation manual. The high-resolution timer provides approximately 13-usec resolution. This is accomplished with an 8-bit hardware register which contains the low-order byte of the timer. Each time the low-order byte counts to zero, the timer value at location 80-82 is decremented at the end of the instruction currently being executed. An operand fetch from location 80 will retrieve the three high-order bytes from location 80 plus the low-order bytes from the hardware register. If the low-order byte has stepped through zero during the instruction, then before a fetch from location 80, zeros are inserted into the low-order byte instead of the contents of the hardware register. Any instruction that stores into location 80 also stores the low-order byte into the hardware register, as well as a full word into location 80. If the timer value at location 80 changes from positive to negative, an external interrution is requested. ... snip ... approx. 15hr interval ... makes bit23 (i.e. bits 0-23) approx. 3mills. ... 360/67 timer required access to location 80 approx. every 3mills or machine would redlight. (bit31) 13microseconds *256 (bit23) is 3.328 milliseconds. 3.328 milliseconds times 2**24 is 15.51 hrs (for 32bits) bit23 at 3.328ms, bit22 at 6.656ms, bit21 at 13.312ms, bit20 at 26.624ms bit19 at 53.248ms, bit18 at 106.496ms, bit17 at 212.992ms misc. past posts mentioning doing clone controller http://www.garlic.com/~lynn/subtopic.html#360pcm -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: CLOCK change problem
bherr...@txfb-ins.com (Herring, Bobby) writes: > TOD Clock switch AFAIK came in with the 370. I remember it > specifically on the 168 my memory is iffy on the 155/158 but I think > it was there, no experience on the 14X . > > If it was there on the 360s I never heard/saw anything about it. TOD was introduced with 370 (interval timer & clock comparator) ... relaxing location 80 timer. i remember getting caught up for a couple months discussing things like whether the TOD baseline of first day of the century was 1900 or 1901. lower-end 360s would update location 80 appox. every 3mills ... higher end 360 could have (high resolution) location 80 update approx every 13mics ... including 360/67. cp/67 used location 80 for everything ... it would save old value and load new value into 84, doing overloaping 8byte move from "80" to "76" (moved old value from 80 into 76 and new value from 84 into 80). It would then update the various clocks and timer values by the difference in current value saved to 76 and the original value that had been originally loaded into 80 (aka virtual machine microseconds used, kernel supervisor microseconds used, current clock value). when cp/67 was originally installed at the univ. in jan68 ... it had support for 1050 & 2741 terminals ... along with "automatic terminal identification". The univ. had some number of ascii/tty terminals ... so I had to add TTY terminal support. I extended the original logic for automatic terminal identification to include TTY. It worked fine for leased lines ... but had a glitch trying to do a single dailin phone number with "hunt group" (pool of lines). It was possible to change line-scanner associated with each port (terminal type) ... but that didn't actually change the line-speed for each port (1050 & 2741 were the same ... but ascii/tty was different). This somewhat prompted the univ. to do a clone controller effort ... reverse engineer channel interface and building channel interface board for Interdata/3 ... and programming Interdata/3 so it could do both line-speed and terminal type. This got four of us written up as responsible for (some part of) clone controller business ... since vendor picked up the implementation and sold it commercially. One of the first bugs testing on channel interface was 360/67 "red-light". The timer-tic hardware attempts to update location 80 on every tic ... if the processor or channel is holding the memory bus interface, it will delay ... but if delays so long that the timer tics again ... it will stop the processor with hardware failure. Turns out the initial clone controller implementation wasn't making sure that it told the channel interface to release the memory bus at least once every 13microseconds. The location 80 timer updates put expensive load on memory bus ... one of the reasons for starting to eliminate its use ... starting with tod, interval timer, and clock comparator in 370. -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: Last card reader?
shmuel+ibm-m...@patriot.net (Shmuel Metz , Seymour J.) writes: > You really mean 709 and not 7090? That's a big jump! re: http://www.garlic.com/~lynn/2011k.html#8 Last card reader? univ. supposedly had something like #3 709, thousands of tubes that constantly required maintenance ... something like "20 ton" air conditioning capacity. much of workload was student fortran ibsys running tape-to-tape (second or two elapsed) ... with 1401 front-end for unit record (carried tape between 709 drives and 1401 drives) there was intermediate step replacing 1401 with 360/30 ... started out with 360/30 running hardware emulation for the MPIO that did the unit-record<->tape. I got student job rewritting MPIO in 360 assembler got to design my own stand-alone monitor, interrupt handlers, device drivers, console interface, etc. then move to os/360 on 360/65 (actually 360/67 spent most of the time running as 360/65, replaced both 709 & 360/30) ... much less heat. student jobs then ran 3step fortran-g, complie, link-edit, & go ... over a minute elapsed time per student jog; hasp got it down to over 30+ seconds elapsed time. I started taking stage-2 sysgens completely apart and put them back together for careful ordering of files and pds members to optimize arm seek ... getting down to a little under 13seconds elapsed time (nearly three times improvement) it wasn't until univ. installed watfor that student job elapsed time got down to 709. the univ. was supposedly getting 360/67 to run tss/360 ... but tss/360 failed to reach any reasonable operational level. eventually did get (virtual machine) cp67 january 1968 ... and the univ. let me play with it on weekends. I rewrote large sections of cp67 before graduating. -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: Last card reader?
chrisma...@belgacom.net (Chris Mason) writes: > The 2540 was an enormously versatile machine in that it not only > supported the card reading function but also the card punching > function. > > http://www.columbia.edu/cu/computinghistory/2540.html > > Google ad: first hit with search words "IBM 2540 picture". > > But, looking at the picture I realise I've forgotten which "feed" was > the reader "feed" and which was the punch "feed"! re: http://www.garlic.com/~lynn/2011k.html#13 Last card reader? reader ran faster than the punch ... punch had hopper for maybe couple hundred cards (on left) ... reader had slopping tray feed (on the right) could get at least a box of cards (2000) bitsavers more detailed 2540 (but poorly scanned ... hard to make out details) http://www.bitsavers.org/pdf/ibm/360/A21-9033-1_2540_CompDescr.pdf 1402 was similar ... lot more detail & better scan: http://www.bitsavers.org/pdf/ibm/140x/231-0002-2_1402_Card_Read-Punch_CE_Manual_1962.pdf bitsaver is also good for older tab machines: http://www.bitsavers.org/pdf/ibm/punchedCard/ -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: Last card reader?
ps2...@yahoo.com (Ed Gould) writes: > Wasn't there a card reader as a requirement for 3090 and before > so the CE could install the OLTEP program and a rudimentary IOCDS to > run his diagnostics? 3092 (3090 service processor) was a pair of 4361s running a special custom vm370 release 6 off of 3370 FBA drives. All that stuff chould have come on 3370 FBA disks as part of the service processor. aka at bottom mentions 3092 requires two 3370 FBA devices (one for each 4361 running vm370): http://www-03.ibm.com/ibm/history/exhibits/mainframe/mainframe_PP3090.html above also mentions that 3092 (aka vm370 4361s) requires access to 3420 tape drive. misc. past posts mentioning 3092: http://www.garlic.com/~lynn/2009b.html#22 Evil weather http://www.garlic.com/~lynn/2009e.html#50 Mainframe Hall of Fame: 17 New Members Added http://www.garlic.com/~lynn/2010e.html#32 Need tool to zap core http://www.garlic.com/~lynn/2010e.html#34 Need tool to zap core http://www.garlic.com/~lynn/2010e.html#38 Need tool to zap core http://www.garlic.com/~lynn/2011c.html#71 IBM and the Computer Revolution http://www.garlic.com/~lynn/2011e.html#62 3090 ... announce 12Feb85 http://www.garlic.com/~lynn/2011f.html#31 TCP/IP Available on MVS When? http://www.garlic.com/~lynn/2011f.html#32 At least two decades back, some gurus predicted that mainframes would disappear http://www.garlic.com/~lynn/2011f.html#42 At least two decades back, some gurus predicted that mainframes would disappear in future and it still has not happened http://www.garlic.com/~lynn/2011h.html#68 IBM Mainframe (1980's) on You tube -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: Last card reader?
steve.do...@ccbcc.com (Steve Dover) writes: > Phil, we had one at Allstate Insurance until 1990. 2540 reader/punch. > I sure miss the chads, they were great fun in desks and cars. But I > do not miss hauling the 50 pound boxes around. as undergraduate in the 60s ... univ. was using sense-marked cards (no.2 pencil) for class registration ... tables in the gym and students would get card for each class and fill in their information. Then cards were run thru and holes punched (solid manilla color cards) registration program was moved from 709 to 360 with 2540 reader/punch. all the cards were in large number of trays (about 3000 per ... about box & half) were fed into the 2540 reader. I wrote subroutine to feed into the middle stacker (stacker 3) ... registration program would validate the registration information and if it found a problem, a blank card would be "punched" behind it (middle stacker, stacker 3 was selectable from both the reader and the punch). The punch had been loaded with top-edge red-stripe cards ... so when everything was done ... it was possible to pick out class registration cards with errors ... by the top red-stripe edge card immediately following it in the tray. -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: Opcode X'A0'
hfdte...@comporium.net (John Baker) writes:
> The X'A0' opcode provided various VS APL Assist functions.
this was done at palo alto science center for 370/145. 370/145 had
loadable microcode from floppy disk ... and would start to take away
high real storage (from processor memory) for microcode.
cambridge science center had taken apl\360 ... removing the monitor and
other stuff ... for running in cms virtual machine ... as cms\apl (also
had to redo how apl managed storage for large virtual memory paged
environment ... the mechanism from apl\360 was guaranteed to page
thrash). misc. past posts mentioning science center
http://www.garlic.com/~lynn/subtopic.html#545tech
misc. past posts mentioning APL (&/or HONE a major internal APL-based
world-wide online sales&marketing support service)
http://www.garlic.com/~lynn/subtopic.html#hone
palo alto science center then did apl\cms for vm370/cms ... as well as
the 145 microcode.
the person that did the apl microcode for 370/145 ... also did a
microcode hot-spot monitor as part of ECPS development. It created a
table of 32byte kernel storage locations and periodic sample the PSW
address ... incrementing the corresponding storage counter ... past
reference to work on deciding parts of kernel to drop in to 138/148
microcode:
http://www.garlic.com/~lynn/94.html#21 370 ECPS VM microcode assist
http://www.garlic.com/~lynn/94.html#27 370 ECPS VM microcode assist
http://www.garlic.com/~lynn/94.html#28 370 ECPS VM microcode assist
palo alto science center also did SCAMP (Special Computer APL Machine
Portable) and ibm/pc ("portable computer") 5100
http://www-03.ibm.com/ibm/history/exhibits/pc/pc_2.html
5150 was 1975 precursor to ibm/pc ("personal computer") 5150
http://www-03.ibm.com/ibm/history/exhibits/pc/pc_1.html
5100 ran "modified" version of (370) apl/sv
http://en.wikipedia.org/wiki/IBM_5100
cp67/cms cms\apl had also provided an API to system services ... which
the APL purists claimed violated the purity of the APL design. However,
it got a whole lot of useage for doing real-world problems (like being
able to read/write files).
apl/360 typically ran with 16kbyte (or 32kbyte) workspaces ... where
everything resided in the workspace (and apl\360 monitor would swap
whole workspace as integral unit).
cms\apl opened workspace size to large virtual memory as well as adding
API to access system services ... and cambridge science center made it
available on its cp67 service. One of the earliest users of this APL on
cambridge service were the business planners in Armonk ... they loaded
the most valuable of corporate assets on the cambridge system (detailed
customer details) and did busines modeling in APL. This required some
pretty good security since the cambridge system was also available to
various students&staff from univ. in the boston/cambridge area.
The APL purists eventually responded to the (cms\apl) system services
API with "shared variables" (that appears in apl/sv)
http://en.wikipedia.org/wiki/APL_Shared_Variables
--
virtualization experience starting Jan1968, online at home since Mar1970
--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO
Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: Suffix of 64 bit instructions
shmuel+ibm-m...@patriot.net (Shmuel Metz , Seymour J.) writes: > The B2 opcodes came later. Some of the emulator features on the S/360 > had longer opcodes. diagnose (x'83') is supervisor instruction defined as model specific. common mechanism was the displacement field was used as "extended op-code" ... selecting specific/specialized microcode functions. one use was invoking microcode emulators (available on various 360 processors) diagnose displacement x"3cc" selects emulator function, turning on/off special emulator instructions (x'99' opcode) ... page 64. http://www.bitsavers.org/pdf/ibm/360/1401_emulator/GC27-6940-4_360_1401emul.pdf and then more/other diagnose variations on page 72. recent post (in afc) discussing above http://www.garlic.com/~lynn/2011h.html#16 Is the magic and romance killed by Windows (and Linux)? as undergraduate in the 60s ... i made a whole bunch of enhancements to cp67. one was special fast dasd ccw for cms file i/o. the guys at the science center slammed me for violating 360 principles of operations ... since such a mechanism wasn't defined for real hardware. they came up with definition that all such special (virtual machine) processing had to be done via "diagnose" instruction using the "fiction" that it virtual machines running under cp67 qualified as a special model (aka conforming to 360 principle of operations as implementation being model specific, in this case, the "virtual machine" model). this kicked off a whole slew of special virtual machine functions (aka "instructions") all selected via the diagnose instruction displacement field. cp67 cms (cambridge monitor system) would run on real 360 ... and as some of the specifial virtual machine features were added, at startup, cms would check for running on real machine or virtual machine (setting switch for using straight real machine processing or optional virtual machine processing). in the morph to vm370, cms was renamed to converstational monitor system and the ability to run on real hardware was crippled. misc. past posts mentioning cambridge science center http://www.garlic.com/~lynn/subtopic.html#545tech -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: assembler help!
peter.far...@broadridge.com (Farley, Peter x23353) writes: > ITYM RL/S (Rand Language for Systems). I was at the SHARE in NY that > year and managed to score a copy of the RL/S manual, but I never had > my hands on a tape. Still have the manual around here somewhere > though. > > If I remember the scuttlebutt correctly, Rand said that they wrote it > in PL/1 and reverse engineered the syntax and semantics from studying > IBM microfiche listings. > > I don't think that any of us have ever understood IBM's paranoia about > PL/S or its successors being in the hands of users. It's just a > language, after all. The only reason anyone I spoke with back then > could imagine was that IBM didn't want PL/S (or any clones) > cannibalizing the use of PL/1, which they were pushing hard, IIRC. > > It would be enlightening if an IBMer of that time at a high enough pay > grade to have participated in those internal discussions would reveal > the real reasons in their autobiography. PL/S was one of the casualties of the FS effort in the 70s ... then when FS was killed off and 370 was being resurrected ... PL/S was slow to get going. This contributed to difficulty getting relational implementation on MVS ... that and EAGAL was the official grand strategic database for MVS ... and so there wasn't a lot of interest for relational (aka DB2) on MVS until after EAGAL had failed. Some of this is mentioned in MIPENVY, copy http://www.garlic.com/~lynn/2007d.html#email800920 in this past post http://www.garlic.com/~lynn/2007d.html#17 Jim Gray Is Missing and from ibm definitions: [MIP envy] n. The term, coined by Jim Gray in 1980, that began the Tandem Memos (q.v.). MIP envy is the coveting of other's facilities - not just the CPU power available to them, but also the languages, editors, debuggers, mail systems and networks. MIP envy is a term every programmer will understand, being another expression of the proverb The grass is always greener on the other side of the fence. [Tandem Memos] n. Something constructive but hard to control; a fresh of breath air (sic). "That's another Tandem Memos." A phrase to worry middle management. It refers to the computer-based conference (widely distributed in 1981) in which many technical personnel expressed dissatisfaction with the tools available to them at that time, and also constructively criticized the way products were [are] developed. The memos are required reading for anyone with a serious interest in quality products. If you have not seen the memos, try reading the November 1981 Datamation summary. ... snip ... I had been blamed for online computer conferencing on the internal network in the late 70s and early 80s. "Tandem Memos" were actually kicked off with report that i wrote after a visit to Jim at Tandem (after he had left IBM). MIPENVY mentions that PLS3 (by the POK tools group) wasn't available on vm370 and dos. Part of this was that in the mad rush to get stuff back in 370 product pipelines (after failure of FS), the head of POK convinced corporate to kill-off vm370, shutdown the vm370 development group, and move all the people to POK (or otherwise they would miss MVS/XA ship date ... nearly 8yrs in the future). As it turned out, Endicott managed to save the vm370 product mission, but had to recreate a development group from scratch. It turns out the plans for the vm370 shutdown was to only give them something like month notice (to minimize potential that they could find alternatives). As it turned out the information was leaked several months early (which kicked off witch hunt to find who leaked the info). Somewhat as a result, several found jobs at DEC working on VAX/VMS (joke that head of POK was a major contributor to early VAX/VMS development) misc. past posts mentioning original relation/sql http://www.garlic.com/~lynn/submain.html#systemr misc. past posts mentioning FS http://www.garlic.com/~lynn/submain.html#futuresys -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: disclosing "business" information on the internet
steve_con...@ao.uscourts.gov (Steve Conway) writes: > From a security standpoint, the less you expose to the outside world, the > better. Join a few security newsgroups / mailing lists, and see what > (justified) paranoia REALLY looks like. we were tangentially involved with the cal. state data breach legislation ... having been brought in to help wordsmith the cal. state electronic signature legislation. several of the parties were heavily involved in privacy issues and had done in-depth public surveys. the number one issue was "identity theft", primarily "account fraud" that were result of some sort of data breach. The issue was little or nothing was being done in this area (the institutions with the breaches frequently had little or nothing at risk, the fraudulent transactions were against their customer accounts). there was some hope that the resulting publicity from the notifications would prompt corrective actions as well as give the public some chance to take countermeasures. in the decade plus since the cal. legislation there have been several federal bills introduced ... somewhat falling into two categories, those similar to the original cal. legislation and "federal pre-emption" that would eliminate most requirements for notification. the most recent federal legislation falls into the later category ... notification only when the records contain long list of personal details (would eliminate nearly all breaches ... including the original reason that prompted cal. legislation ... simple account numbers that can result in fraudulent financial transactions). -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: disclosing "business" information on the internet
eamacn...@yahoo.ca (Ted MacNEIL) writes: > Recently, I worked at a shop where our VP told us we must have all > that info in our signature block -- quite the opposite! a group of us were the first to have business cards made up with our internal newtwork email address (as well as arpanet email address). some people complained ... with an excuse that business cards were only for use with customers ... who wouldn't be able to contact us on the internal network. now it turned out that for quite some time, it was common to have business cards with both external phone number and the internal corporate tieline number ... for use with both customers and internal corporate colleagues ... so the internal email address was just the equivalent of the internal corporate tieline number (aka whole thing prompted by individals that weren't comfortable with this new fangled email stuff). old post: http://www.garlic.com/~lynn/internet.htm#0 http://www.garlic.com/~lynn/98.html#59 with email regarding the email gateway between arpanet/internet and the internal network: http://www.garlic.com/~lynn/98.html#email821022 -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: disclosing "business" information on the internet
rfocht...@ync.net (Rick Fochtman) writes: > My two cents' worth: that auditor needs to find a more challenging > shop. He's "nit-picking" on trivia and showing just how paranoid he > really is. Too much time on his hands. one of the biggest challenges when we started doing the (internal) online telephone book were the plant site security officers. we wanted the softcopy of original source used for printed plantsite telephone books (which were unclassified or internal use only). almost uniformly plant site security officers (and random other individuals) would claim that making the same information available online (internal only systems) would be a security risk (and should require much higher security classification ... like "ibm confidential" or "confidential-restricted"). we eventually were able to convince security officer at one large corporate plantsite ... and then used that location as an argument with all the other plantsite security officers. by '83 or so ... it was all over ... but it was really tough slogging with security officers (and random other security want-a-bees) for a time ... the internal network was larger than the arpanet/internet from just about the beginning until possibly late '85 or early '86 (vast majority were vm370 systems ... even for operations that were primarily mvs development). misc. past posts mentining internal network http://www.garlic.com/~lynn/subnetwork.html#internalnet old post with corporate locations that new/added nodes during 1983: http://www.garlic.com/~lynn/2006k.html#8 one of the big divergence between internal network and internet in the mid-80s ... was the communication group forcing PCs and workstations to be limited to terminal emulation ... while the internet was starting to see big explosion in PCs and workstations as (peer) network nodes. on the other hand ... this item from today Experts complacent about network attacks: Study shows physical attacks to communications network infrastructure deemed low priority risk http://www.sciencedaily.com/releases/2011/07/110728111452.htm early 80s, security study prompting special corporate encrypting modems for home&traveling terminal program identified (physical compromise of) hotel pbx system as major vulnerability. on the other hand ... one of the early installations of the modems was at home for senior executive ... who had EE background. he was testing the contacts with his tongue when the phone rang ... which resulted in directive that all future modems made by the corporation had to have the phone jack contacts recessed far enough that they couldn't be touched by the tongue of babies and senior executives (which frequently makes it difficult to remove phone connection). -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: Check out June 2011 | TOP500 Supercomputing Sites
efinnel...@aol.com (Ed Finnell) writes: > _June 2011 | TOP500 Supercomputing Sites_ > (http://www.top500.org/lists/2011/06) > > That's a whollottaflops... and a whole lot of sparcs ... regardless of what sun/oracle is doing. recent comment (in linkedin) thread that possibly a blade mega-datacenter may have more MIPs than the aggregate of all currently installed mainframes: http://www.garlic.com/~lynn/2011i.html#9 At least two decades back, some gurus predicted that mainframes would disappear in future and it still has not happened note that original 64bit sparc was being done at HAL (initials from former head of ibm 801/risc workstation division and head of sun manufacturing, there was glitch at last minute with sun objecting to participation by former sun employee) ... heavily funded by fujitsu ... eventually absorbed into fujitsu. http://en.wikipedia.org/wiki/HAL_Computer_Systems misc. past posts mentioning 801, risc, romp, rios, power, power/pc, etc http://www.garlic.com/~lynn/subtopic.html#801 -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: NYTimes: IBM, helped by new mainframe sales, exceeds analysts' expectations
john_w_gilm...@msn.com (john gilmore) writes: > This morning's New York Times, which perhaps not quite all of you see, > contains a piece attributing IBM's unexpectedly good financial results > to sales of new mainframes. from bloomberg/businessweek IBM Gains After Raising Profit Forecast on Software Demand http://www.businessweek.com/news/2011-07-19/ibm-gains-after-raising-profit-forecast-on-software-demand.html from above: Software sales advanced 17 percent, evidence that Chief Executive Officer Sam Palmisano is making headway on efforts to bulk up in that area, in addition to services, IBM's mainstay. Together, the divisions accounted for 80 percent of IBM's sales in the quarter, up from 65 percent a decade earlier. ... snip ... -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: Making Z/OS easier - Effectively replacing JCL with Unix like commands
charl...@mcn.org (Charles Mills) writes: > Somewhat OT but why? Why not C on the mainframe? Why two code bases, one > fairly easy to debug and one relatively hard to debug? > > I am thrilled with writing software for the mainframe in C (C++ actually) > after years of laboring in assembler. the los gatos vlsi lab was using metaware for a lot of (mainframe) vlsi tool development. two people from the group then di mainframe pascal compiler ... which eventually evolved into vs/pascal product. I was working on getting one of the people (responsible for mainframe pascal) to do C language front-end ... when he left and went to work for metaware. when the palo alto group was planning on doing BSD unix for mainframe, I talked them into contracting with metaware for the C compiler. However, before that mainframe BSD unix shipped, the group was retargeted to PC/RT ... eventually coming out with "AOS" (bsd unix running on pc/rt) ... but still using metaware's c compiler. the disk division eventually sponsored the posix support on MVS ... one of the many things they were doing to try and get around the stranglehold that the communication group had on the mainframe datacenter (most of which the communication group vetoed ... since the communication group had strategic ownership for everything that crossed the datacenter walls; disk division being hdqtrd in silicon valley possibly helped with their perspective) misc past posts mentioning disk division talk at annual, internal, world-wide communication group conference that started out with the statement that the communication group was going to be responsible for the demise of the disk division (the communication group stranglehold was already resulting in data fleeing the mainframe datacenter to more distributed computing friendly platforms). http://www.garlic.com/~lynn/subnetwork.html#terminal a co-worker that helped with the original CMSBACK (eventually morphs into today's TSM) ... misc. past posts http://www.garlic.com/~lynn/submain.html#backup ... left and did a lot of consulting for various silicon valley chip shops. At one place, he did a lot of work and enhancements for the AT&T C compiler (and some number of other vendor C compilers) for their operations on mainframe (as part of porting BSD vlsi tools to the mainframe). At one point he was doing a lot of work doing mainframe ethernet support as part of supporting SGI graphics workstations for displaying VLSI designs. The salesman dropped in and asked him what was going on and after being told, the salesman suggested that he should be doing token-ring support instead (or otherwise the customer might find mainframe support and maintenance suffering). Afterwards, I got a phone call and had to listen to several hours of comments about the company, local branch office and salesmen. The next morning, the vlsi company had big press release that they were moving off mainframe to servers. -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: FW: Mysterious Email (original had no subject)
ba...@mxg.com (Barry Merrill) writes: > "PROFS was Ollie North's downfall" > > Actually, it was the site's VERY GOOD backup philosophy that > kept backups long-term, and the PROFS implementation at that > site that when the user "deleted" a message, it wasn't deleted. almost every such datacenter operation from the period kept long-term backup tapes ... and there wasn't any process to propogate a delete message operation through those backup tapes. for even more drift, recent thread in this mailing list with some PROFs (regarding gov. installation): http://www.garlic.com/~lynn/2011g.html#73 We list every company in the world that has a mainframe computer http://www.garlic.com/~lynn/2011g.html#74 We list every company in the world that has a mainframe computer http://www.garlic.com/~lynn/2011g.html#75 We list every company in the world that has a mainframe computer http://www.garlic.com/~lynn/2011h.html#0 We list every company in the world that has a mainframe computer of other drift, past posts mentioning backup/archive http://www.garlic.com/~lynn/submain.html#backup -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: Web version of mainframes
jagadish...@gmail.com (jagadishan perumal) writes: > Just wanted to know whether a web version of mainframe can be implemented. > One of our user is trying to access from a remote location using a wireless > internet in which the IP changes everytime. first web server outside cern on slac vm/cms (mainframe) system: http://www.slac.stanford.edu/history/earlyweb/history.shtml above mentions jan92, Berners-Lee demonstrats the SLAC connection at a computing workshop in southern France. sgml morphs into html at cern http://infomesh.net/html/history/early gml invented at science center in 1969 ... and gml tag processing added to cms script document processing. decade later gml morphs into sgml .. and another decade morphs into html. from earlier thread (here) on inventor of email http://www.garlic.com/~lynn/2011h.html#49 -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: Vector processors on the 3090
rkueb...@tsys.com (Kirk Talman) writes: > If this is the beast I think it is, it attached only to 360s as a channel > that had outboard channels. Memory (no bit correction) says that was 44, > 65, 75, 91, and 165/8 on 370. May be more. The "programs" were channel > programs. I was told that this was the reason the 44 was created. And > that it was 65 + lobotomy. bitsavers 360/44 funtional characteristics: http://www.bitsavers.org/pdf/ibm/360/funcChar/A22-6875-5_360-44_funcChar.pdf from above: Although the Model 44 processing unis is about the same in physical size (Figure 1) as that of its nearest neighbor, the Model 50, its performance on problems for which it is optimized is 30 to 60 per cent faster than that of Model 50. .. snip .. and: Processor storage speed for the Model 44 is 1 microsecond. Four bytes (one word or two halfwords) are stored or fetched in each access. Processor stroage, alwasy housed within the CPU, is availabe in the four capacities shown at the top of Figure 3. Data paths throughout the CPU are one word wide. .. snip ... functional characteristic for 360/40 (also on bitsaver) has two-byte datapaths bitsaver is missing 360/50 functional characteristics 360/65 had 8byte data paths with 750ns memory low-end & mid-range 360s (up to 360/50) had integrated channels, higher-end 360s (starting with 360/65) had external channels -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: Vector processors on the 3090
l...@garlic.com (Anne & Lynn Wheeler) writes: > try search "linkpak 3090 vf" for various other refs finger slip ... that should be linpack (not linkpak) http://en.wikipedia.org/wiki/LINPACK first top 500 doesn't have ibm mainframe http://www.top500.org/list/1993/06/100 old post w/s-computer sep86 list of supercomputers on bitnet (post previously refed): http://www.garlic.com/~lynn/2000c.html#61 TF-1 lists a couple 3090/VF -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: Vector processors on the 3090
timothy.sipp...@us.ibm.com (Timothy Sipples) writes:
> That's not really true. For example, there was the IBM Engineering and
> Scientific Subroutine Library (ESSL) Vector and Scalar/370 software. That
> software provided a library of mathematical functions you could call from
> FORTRAN, C, PL/I, APL2, or Assembler programs on MVS or VM. It was also
> supported for the languages that ran on AIX/ESA. Program number was
> 5688-226, and it was withdrawn from marketing in 2001. VS FORTRAN Version 2
> (not sure which release) also had some automatic vector support of its own.
>
> The Vector Facility for 3090s was announced on October 1, 1985.
> Announcement letter 185-121 is still available on IBM's announcements Web
> site (http://www.ibm.com/common/ssi). At the time you could rent your first
> Vector Facility for a list price of $30,830 per month and any subsequent
> VFs for $19,170 per month. The purchases prices were $370,000 and $230,000,
> respectively. All prices are in 1985 dollars, of course.
>
> Before that there was the IBM 3838 Array Processor which ran (eventually)
> the Vector Processing Subsystem (VPSS)/XA. I think the 3838 debuted in 1976
> or 1977. Your VPSS stuff could run on the VFs using (what else) VPSS/VF.
> VPSS/XA was IBM Program Number 5665-301. VPS/XA also supported FORTRAN, at
> least.
>
> And before *that* there was the IBM 2938 Array Processor which you attached
> to your System/360.
>
> By the way, you could think of today's zEnterprise BladeCenter Extension
> (zBX) as a mainframe vector processor...plus lots of other capabilities.
re:
http://www.garlic.com/~lynn/2011h.html#68 IBM Mainframe (1980's) on You tube
http://www.garlic.com/~lynn/2011h.html#69 IBM Mainframe (1980's) on You tube
http://www.garlic.com/~lynn/2011h.html#72 Vector processors on the 3090
http://www.garlic.com/~lynn/2011h.html#73 Vector processors on the 3090
there were a couple groups in kingston ... one was the E&S center that
had a 3090VF (as well as 20 Floating Point Systems boxes) and the group
that was supposedly designing an IBM supercomputer ... but was also
funding/supporting various other activities ... like the HiPPI I/O
interface for 3090 and providing funding for Chen Supercomputer company.
long winded thread in a.f.c. from last year
http://www.garlic.com/~lynn/2010b.html#71 Happy DEC-10 Day
http://www.garlic.com/~lynn/2010b.html#72 Happy DEC-10 Day
http://www.garlic.com/~lynn/2010b.html#73 Happy DEC-10 Day
http://www.garlic.com/~lynn/2010b.html#74 Happy DEC-10 Day
and later thread in comp.arch
http://www.garlic.com/~lynn/2010f.html#47 Nonlinear systems and nonlocal
supercomputing
http://www.garlic.com/~lynn/2010f.html#48 Nonlinear systems and nonlocal
supercomputing
http://www.garlic.com/~lynn/2010f.html#49 Nonlinear systems and nonlocal
supercomputing
http://www.garlic.com/~lynn/2010f.html#50 Nonlinear systems and nonlocal
supercomputing
As mentioned in above, oct91, the senior executive sponsonsoring the
supercomputer effort retired and there was lots of review of various
projects. then there was an effort to canvas the company to find
something for supercomputer (they found the effort I was doing in
mid-jan92, and over a couple weeks, it was transferred to Kingston, we
were told we couldn't work on anything with than four more processors
and it was announced as supercomputer). misc. email from late 91 & early
92
http://www.garlic.com/~lynn/lhwemail.html#medusa
This old post describes the ('87) cornell national supercomputer
facility with 3090-400 VF and five FPS boxes
http://www.garlic.com/~lynn/200c.html#2000c.html#61 TF-1
some followon in this old thread:
http://www.garlic.com/~lynn/2000d.html#2 IBM's "ASCI White" and "Big Blue"
architecture?
http://www.garlic.com/~lynn/2000d.html#3 IBM's "ASCI White" and "Big Blue"
architecture?
http://www.garlic.com/~lynn/2000d.html#8 IBM's "ASCI White" and "Big Blue"
architecture?
above references the 1.5gflops peak for 375mhz power3-ii chip is
approx. same as the aggregate for IBM Kingston E&S lab in 1985 (with all
the FPS boxes)
HiPPI was the standards version of Cray 100mbyte/sec parallel (aka
half-duplex) channel (standards effort driven out of LANL). 3090 I/O
wasn't capable of handle the rate ... so a hack was done in the side of
3090 extended store bus ... with peek/poke semantics; aka basicaly i/o
commands & data were read/written to special addresses on the 3090
extended store bus. Later there was serial-HiPPI (with fiber) which then
sort of merges with FCS (standards effort driven out of LLNL for 1gbit
fiber full-duplex; POK gets involved and there is now FICON flavor of
FCS).
--
virtualization experience starting Jan1968, online at home since Mar1970
--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO
Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: Vector processors on the 3090
ps2...@yahoo.com (Ed Gould) writes: > All the google searches are mute (or Cost $$$) > > As to the mega flops the facility had. Anyone have the numbers? > > Sorry to ask these semi off topic question but I was asked about them > and am at a loss to find documentation that doesn't. Cost $$ > > As a side question anyone work with the facility? Any stories you > would like to share would be interesting. see previous post reference http://www.garlic.com/~lynn/2011h.html#68 IBM Mainframe (1980's) on You tube ... which includes mflop ranking numbers, here http://www.garlic.com/~lynn/2002i.html#12 CDC6600 - just how powerful a machine was it? references table that has gone 404 ... but still available at wayback machine from table: IBM ES/9000-511 VF(1 proc 11ns) 30 IBM ES/9000-340 VF (14.5 ns) 23 IBM ES/9000-320 VF (1 proc 15 ns) 22 IBM ES/9000 Model 260 VF (15 ns) 19 IBM ES/9000 Model 210 VF (15 ns) 17 IBM 3090/180J VF (1 proc, 14.5 ns)16 IBM ES/9000 Model 190 VF(15 ns) 14 IBM 3090/180E VF 13 try search "linkpak 3090 vf" for various other refs http://publishing.cdlib.org/ucpressebooks/view?docId=ft0f59n73z&chunk.id=d0e7046&toc.id=d0e7005&brand=ucpress;query=architecture http://www.netlib.org/performance/rank/linpack/ ftp://icmsec.cc.ac.cn/pub/netlib/performance/html/linpack-peak.data.col0.html http://www.taborcommunications.com/archives/3053.html http://www.sdsc.edu/Xtal/Bm/benchmark_results other posts in previous thread: http://www.garlic.com/~lynn/2011h.html#69 IBM Mainframe (1980's) on You tube http://www.garlic.com/~lynn/2011h.html#70 IBM Mainframe (1980's) on You tube -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: IBM Mainframe (1980's) on You tube
l...@garlic.com (Anne & Lynn Wheeler) writes: > IBM TSS/360 pubs at bitsavers: > http://www.bitsavers.org/pdf/ibm/360/tss/ re: http://www.garlic.com/~lynn/2011h.html#68 IBM Mainframe (1980's) on You tube http://www.garlic.com/~lynn/2011h.html#69 IBM Mainframe (1980's) on You tube one of the things in tss/360 was "single-level-store" ... basically virtual memory semantics for files. there was some number of implementation difficulties ... which continued into the FS effort. ... misc. past posts http://www.garlic.com/~lynn/submain.html#futuresys After FS failed, some subset was carried forth for the s/38 in Rochester (later morphing into as/400). some number of things carried forth from CTSS into cp67/cms ... but CMS also adopted a bunch of os/360 stuff (compiler, assemblers, etc) by simulating some amount of os/360 system services. during the FS period ... I was doing some memory mapped stuff for cp67/cms ... attempting to avoid many of the shortcomings that I observed from tss/360 (and ridiculing the FS effort, claiming I had some amount of stuff running that they just had vaporware descriptions). misc. past posts http://www.garlic.com/~lynn/submain.html#mmap However, tss/360 did (at least) one thing correct and that was the definition of address constants; it was possible to memory-map an executable image on disk directly into a virtual address space at any location/address (w/o needing to perform any additional operations) ... including being able to have identical shared copy of the same executable images in different virtual address spaces simultaneously at different addresses. By comparison, the os/360 semantics for "relocatable address constants" (started out) bringing the executable image into (real) storage at a specific location ... and then running through the (real) storage image adjusting all the "relocatable address constants" (to correspond to their loaded address). For memory-mapped implementation, this represented horrible post-processing work ... precluding automically having exact page-mapped image (whats on disk and whats in memory are identical) *and* sharing between different virtual address spaces potentially at different virtual addresses. I had constant on-going headache attempting to deal with all of the os/360 semantics that had been incorporated into CMS making the transition to memory-mapped paradigm ... misc. past posts mentioning headaches trying to deal with the os/360 relocatable adcon semantics (in paged mapped environment): http://www.garlic.com/~lynn/submain.html#adcons I then ported a bunch of the stuff from cp67/cms to vm370/cms ... a couple old email refs: http://www.garlic.com/~lynn/2006v.html#email731212 http://www.garlic.com/~lynn/2006w.html#email750102 http://www.garlic.com/~lynn/2006w.html#email750430 above mentions csc/vm distirbution ... one of my hobbies was providing production operation systems for internal datacenters. At one point, csc/vm was distributed and run at more internal datacenters than the total, aggregate number of Multics installations (small rivalry between the science center on 4th flr and multics on 5th flr). the mad rush to get products back into the 370 hardware and software product pipelines (after FS failure) ... contributed to picking up and releasing a subset of the csc/vm code in standard shipped vm370 product. -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: IBM Mainframe (1980's) on You tube
mike.a.sch...@gmail.com (Mike Schwab) writes: > Vector processors. Instruction Op-codes were re-used for z/Series. > > So Hercules was consolidated into 3 models. Latest S/370 with 64MB > real, XA through S/390 with vector, and z/Series. Earlier models > would run on the last model, just the software would not use > instructions for after the model they were coded for. I think they > are even trying for a S/360-67 for Multics with virtual memory add-on. some number of people from CTSS (ibm 7094) went to science center on the 4th floor, 545 tech sq, and did cp40 on 360/40 with specially modified virtual memory hardware (they had originally tried for a 360/50, but all the spare 360/50s were going to the FAA air traffic control effort) misc. past posts mentioning 545 tech sq http://www.garlic.com/~lynn/subtopic.html#545 some number of other people from CTSS went to Project Mac/Multics on 5th floor. the science center was pushing hard that Project Mac select 360/67 (standard IBM product with virtual memory support, basically 360/65 with the virtual memory hardware add-on) for Multics. However, Project Mac selected GE645 for Multics. IBM (also) started official time-sharing TSS/360 product for 360/67. The science center worked on morphing cp40 into cp67 for 360/67 (in parallel with tss/360 ... folklore is cp67 at one point had 12 people working on cp/67 at the same time that tss/360 had 100 times more ... approx 1200 people). There was various internal politics between the tss/360 group and the (virtual machine) cp67 group at the science center. Quite a bit of that early history is covered in Melinda's paper ... original in multipart postscript http://web.me.com/melinda.varian/Site/Melinda_Varians_Home_Page.html recently I sent Melinda a merged single file PDF version http://web.me.com/melinda.varian/Site/Melinda_Varians_Home_Page_files/neuvm.pdf and a kindle version http://web.me.com/melinda.varian/Site/Melinda_Varians_Home_Page_files/neuvm.azw IBM TSS/360 pubs at bitsavers: http://www.bitsavers.org/pdf/ibm/360/tss/ Multics was originally implemented in PLI ... GE computer business was bought by Honeywell (including commercial Multics) and recently the Multics source was made available ... lots more at Multics site (and there is reports of work on hardware simulation to run Multics) http://www.multicians.org Some mention of using cp67 for keeping SE skills sharp in recent (linkedin IBM employee) discussion about 23jun69 unbundling announce: http://www.garlic.com/~lynn/2011h.html#61 Do you remember back to June 23, 1969 when IBM unbundled http://www.garlic.com/~lynn/2011h.html#62 Do you remember back to June 23, 1969 when IBM unbundled http://www.garlic.com/~lynn/2011h.html#63 Do you remember back to June 23, 1969 when IBM unbundled other recent discussion of CTSS, Multics, science center, tech sq http://www.garlic.com/~lynn/2011h.html#44 OT The inventor of Email - Tom Van Vleck http://www.garlic.com/~lynn/2011h.html#49 OT The inventor of Email - Tom Van Vleck http://www.garlic.com/~lynn/2011h.html#51 Did My Brother Invent E-Mail With Tom Van Vleck? http://www.garlic.com/~lynn/2011h.html#54 Did My Brother Invent E-Mail With Tom Van Vleck? The cp67 development group split off from the science center and took over (IBM) Boston Programming Center on the 3rd floor ... with the morph of cp67 into vm370 and rapid growth ... the group outgrew the 3rd floor and moved out to the old (empty) SBC (given to CDC in some litigation settlement) bldg. in Burlington mall. misc. recent post mentioning another occupant of the 3rd flr: http://www.garlic.com/~lynn/2011.html#15 545 Tech Square misc. recent posts mentioning Burlington mall "group": http://www.garlic.com/~lynn/2011.html#18 IBM Future System http://www.garlic.com/~lynn/2011b.html#70 vm/370 3081 http://www.garlic.com/~lynn/2011c.html#83 IBM Future System http://www.garlic.com/~lynn/2011d.html#52 Maybe off topic http://www.garlic.com/~lynn/2011f.html#39 At least two decades back, some gurus predicted that mainframes would disappear in future and it still has not happened http://www.garlic.com/~lynn/2011g.html#8 Is the magic and romance killed by Windows (and Linux)? -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: IBM Mainframe (1980's) on You tube
ps2...@yahoo.com (Ed Gould) writes: > Another topic. What was the IBM # for the specialized processor engines that > were something like AP's (but weren't) on the 3090. I keep coming up with a > 3088, but I know thats not correct. If I could remember more I could google > but > the number is just not coming forth. > > The real question is did anyone know of any that were used (if so for what?). 3088 was trotter ... 8-arm channel-to-channel there were the vm/4361s that ran special modified version of vm370 release 6 that were the "service processors" on the 3090 ... aka 3092 http://www.garlic.com/~lynn/2004p.html#37 IBM 3614 and 3624 ATM's http://www.garlic.com/~lynn/2008i.html#10 Different Implementations of VLIW http://www.garlic.com/~lynn/2009b.html#22 Evil weather http://www.garlic.com/~lynn/2009e.html#50 Mainframe Hall of Fame: 17 New Members Added http://www.garlic.com/~lynn/2011c.html#71 IBM and the Computer Revolution http://www.garlic.com/~lynn/2011e.html#62 3090 ... announce 12Feb85 http://www.garlic.com/~lynn/2011f.html#31 TCP/IP Available on MVS When? http://www.garlic.com/~lynn/2011f.html#32 At least two decades back, some gurus predicted that mainframes would disappear http://www.garlic.com/~lynn/2011f.html#42 At least two decades back, some gurus predicted that mainframes would disappear in future and it still has not happened 3090 had "VF" vector processor facility feature ... misc. past posts mentioning 3090VF http://www.garlic.com/~lynn/2000c.html#61 TF-1 http://www.garlic.com/~lynn/2002i.html#12 CDC6600 - just how powerful a machine was it? http://www.garlic.com/~lynn/2003g.html#68 IBM zSeries in HPC http://www.garlic.com/~lynn/2005m.html#20 simd for 390(or z990)? http://www.garlic.com/~lynn/2006m.html#4 The Power of the NORC http://www.garlic.com/~lynn/2007.html#45 Just another example of mainframe costs http://www.garlic.com/~lynn/2007.html#46 How many 36-bit Unix ports in the old days? http://www.garlic.com/~lynn/2007q.html#55 IBM Z6 processor 3090 was trout1.5 ... misc. past posts w/old email discussing trout1.5 http://www.garlic.com/~lynn/2003j.html#42 Flash 10208 http://www.garlic.com/~lynn/2006j.html#27 virtual memory http://www.garlic.com/~lynn/2009r.html#49 "Portable" data centers http://www.garlic.com/~lynn/2010e.html#44 Need tool to zap core http://www.garlic.com/~lynn/2010k.html#72 "SIE" on a RISC architecture http://www.garlic.com/~lynn/2010m.html#55 z millicode: where does it reside? long ago and far away, my wife had been con'ed into going to POK to be responsible for loosely-coupled architecture. While there there were ongoing skirmishes and temporary truces over mandate to use SNA for loosely-coupled operation (temporary truce would be that she could use anything she wanted within the walls of the datacenter but the communication group own corporate strategic responsibility for everything that cross datacenter walls). While there she also developed "peer-coupled shared data" architecture which saw little uptake until sysplex (except for IMS hot-standby) as well as enhancements to 3088 that improved its use for loosely-coupled operation (which didn't ship). misc. past posts reference "peer-coupled shared data" architecture http://www.garlic.com/~lynn/submain.html#shareddata there was internal effort that used 3088 with cluster of eight vm/4341s for processor complex ... but before they were able to ship as product, they had to convert the interprocessor communication to SNA ... and cluster operations that had taken small faction of a second elapsed time, went to large fraction of a minute. misc. past posts mentioning trotter http://www.garlic.com/~lynn/2001b.html#73 7090 vs. 7094 etc. http://www.garlic.com/~lynn/2002e.html#25 Crazy idea: has it been done? http://www.garlic.com/~lynn/2002f.html#6 Blade architectures http://www.garlic.com/~lynn/2002h.html#26 Future architecture http://www.garlic.com/~lynn/2003d.html#67 unix http://www.garlic.com/~lynn/2003i.html#70 A few Z990 Gee-Wiz stats http://www.garlic.com/~lynn/2004p.html#49 History of C http://www.garlic.com/~lynn/2005.html#11 CAS and LL/SC http://www.garlic.com/~lynn/2005n.html#7 54 Processors? http://www.garlic.com/~lynn/2006c.html#43 IBM 610 workstation computer http://www.garlic.com/~lynn/2006j.html#31 virtual memory http://www.garlic.com/~lynn/2006k.html#21 Sending CONSOLE/SYSLOG To Off-Mainframe Server http://www.garlic.com/~lynn/2006l.html#4 Google Architecture http://www.garlic.com/~lynn/2006r.html#4 Was FORTRAN buggy? http://www.garlic.com/~lynn/2007j.html#71 John W. Backus, 82, Fortran developer, dies http://www.garlic.com/~lynn/2007o.html#72 FICON tape drive? http://www.garlic.com/~lynn/2008d.html#64 Interesting ibm about the myths of the Mainframe http://www.garlic.com/~lynn/2008e.html#73 Convergent Technologies vs Sun http://www.garlic.com/~lynn/2008o.html#57 Virtual http://www.garlic.com/~lynn/2008r.html#72 Curiousity: largest parallel sysplex around? http://www.garlic.com/~lynn/2010f
Re: DR Plans
eamacn...@yahoo.ca (Ted MacNEIL) writes: > Considering the circumstances of a disaster, it wouldn't amaze me. In > 1969, the Canadian government started forcing all financial > institutions, over a certain size, to implement a DR plan, and test > it. In the 90s, major ATM transaction processing center in New Jersey had roof collapse over the week (from snow). Its D/R site had been on something like 5th flr of WTC ... but had recently been taken out by the incident in WTC garage. we were doing ha/cmp and out marketing I had coined terms disaster survivability and geographic survivability ... to differentiate from disaster/recovery. I had also been asked to write a section for the corporate continuous availability strategy document ... but it got remove when both Rochester & POK complained that they couldn't meet the requirements. misc. past posts mentioning availability, disaster survivability, and/or geographic surviviability http://www.garlic.com/~lynn/submain.html#available -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: OT The inventor of Email - Tom Van Vleck
shmuel+ibm-m...@patriot.net (Shmuel Metz , Seymour J.) writes: > It's older than that. re: http://www.garlic.com/~lynn/2011h.html#44 OT The inventor of Email - Tom Van Vleck besides: http://www.multicians.org/thvv/mail-history.html other CTSS reference pages by Tom http://www.multicians.org/thvv/7094.html from above: Notable CTSS Applications - Electronic Mail There were a few other significant improvements about that same time, some contributed by the user community. Noel Morris and I wrote a command, suggested by Glenda Schroeder and Louis Pouzin, called MAIL, which allowed users to send text messages to each other; this was one of the earliest electronic mail facilities. (I am told that the Q-32 system also had a MAIL command in 1965.) ... snip ... and from above: Bob Creasy wrote "The Origin of the VM/370 Time-sharing System" in the IBM Journal of Research and Development, Vol. 25, No. 5, September 1981. This article describes the roots of CP/CMS in CTSS. ... snip ... also from above: RUNOFF Jerry Saltzer wrote one of the very first computer word processing programs, RUNOFF, for CTSS in 1963 and 1964. This program is the ancestor of Unix roff, nroff, and similar text formatting facilities for many other systems. Users edited the input files for RUNOFF with a special editor, TYPSET, that supported upper and lower case letters. Jerry has placed the original CTSS documentation for RUNOFF online as Manuscript Typing and Editing (from Patricia Crisman, editor, The Compatible Time-Sharing System, A Programmers Guide. Second edition. M. I. T. Press, 1965, section AH.9.01, December 1966 revision) and TYPSET and RUNOFF, memorandum editor and type-out commands, M.I.T. Computation Center Memorandum CC-244 / M.I.T. Project MAC Memorandum MAC-M-193. November 6, 1964. The source of RUNOFF is included in the Pierce Collection tapes. ... snip ... At the science center, Madnick did redo of RUNOFF for cp67/cms called script (using very similar formating commands). Then in 69, "G", "M", and "L" invented GML at the science center and gml tag processing was added to script. A decade later GML morphs into SGML ... and then another decade, SGML morphs into HTML (at CERN): reference to SGML to HTML morph: http://infomesh.net/html/history/early misc. past posts mentioning GML, SGML, etc at science center http://www.garlic.com/~lynn/submain.html#sgml misc. past posts mentioning science center http://www.garlic.com/~lynn/subtopic.html#545tech -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: OT The inventor of Email - Tom Van Vleck
ps2...@yahoo.com (Ed Gould) writes: > http://www.multicians.org/thvv/mail-history.html more off-topic ... some number of people from CTSS went to the science center on 4th flr, 545 tech sq. and did (virtual machine) cp40 (on 360/40 with hardware modifications to support virtual memory) ... which then morphs into cp67 when 360/67 became available (and later morphs into vm370). cp40/cms & cp67/cms inherits a lot from ctss. ... others went from CTSS to multics (project mac) on 5th flr, 545 tech sq. misc. past posts mentioning science center &/or 545 tech sq http://www.garlic.com/~lynn/subtopic.html#545tech another of Tom's stories about cp67 and USL (datacenter in another tech sq bldg. across the courtyard from 545) http://www.multicians.org/thvv/360-67.html I had done tty/ascii terminal support in cp67 at univ. as undergraduate and had played some game with using one byte length field. Tom (at USL) later modified max. length for TTY to something like 1200 (I think it was some sort of ascii device plotter down at Harvard). The length calculations then resulted in negative number which gets truncated to very large length and a storage overlay. Base cp67 did dynamic terminal type identification using terminal controller "SAD" command to change line-scanner associated with specific port (for 1052 & 2741). Changes i added for tty/ascii attempted to maintain the dynamic terminal type identification. I then wanted to do single dial-in line for all terminals (using hunt group mapping a single number to a pool). Turns out that 2702 had hardware shortcut & hardwired line speed for each port (separate from being able to dynamically change line-scanner). Dynamic worked between 2741, 1052, & tty for leased lines (where line speed was fixed) ... but wouldn't work for a single pool for all dial-ins. This somewhat prompted univ. to start a clone controller project that would do both dynamic line-speed and dynamic terminal-type. Later four of us get written up as blamed for (some part of) clone controller business. misc. past posts http://www.garlic.com/~lynn/subtopic.html#360pcm there was recent mention on facebook of early domain names http://www.whoisd.com/oldestcom.php I also pointed out old email involving 9-net http://www.garlic.com/~lynn/2006j.html#email881216 also mentioned that Postel (mentioned in previous references), use to let me do section 6.10 in STD1. old reference to interconnecting internal network and csnet/arpanet (mostly for email) http://www.garlic.com/~lynn/internet.htm#0 and this email http://www.garlic.com/~lynn/internet.htm#email821010 the ibm internal network had been larger than the arpanet/internet from just about the beginning until late '85 or possibly early '86 ... misc. past posts http://www.garlic.com/~lynn/subnetwork.html#internalnet recent references to computer conferencing mailing lists on bitnet/earn (where existing ibm-main originated): http://www.garlic.com/~lynn/2011c.html#31 If IBM Hadn't Bet the Company http://www.garlic.com/~lynn/2011f.html#78 Wylbur, Orvyl, Milton, CRBE/CRJE were all used (and sometimes liked) in the past in the late 70s and early 80s, I got blamed for computer conferencing on the internal network; folklore was when the executive committee was informed of internal network & computer conferencing, 5of6 wanted to fire me; (aka at least chairman, ceo, president, etc). -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: An upbeat story
bi...@mainstar.com (Bill Fairchild) writes: > A long time ago a friend of mine told me that the mental abilities to > do computer programming, music, and foreign languages are probably > linked genetically. Since then I have noticed a lot of anecdotal > evidence to support this theory, including myself. But I have also > found a lot of people who are strong in only one of those three > possibly interrelated skills. a least one of the scenarios is whether a person becomes as fluent in a computer language as in their native language ... one of the supposed traits of fluency is actually "thinking" & "dreaming" in a language (as opposed to constantly translating between the language they are working in and some other language that they think in). anecdotal stories are people that have had dreams in a "computer" language. -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: When is performance really an issue? Was: Running an ISPF applicction from one pds
scott.r...@joann.com (Scott Rowe) writes: > If it bothers you that much you are going to have to go back to running on > older (slower) hardware. It is just not possible without throwing out all > the innovative features that allow current processors to run at the speeds > they do. If you think it's bad now, it will get a lot worse if/when IBM > introduces SMT in mainframe CPUs. there was project to do threading for 370/195 (that never shipped). 195 had pipeline and peaked around 10MIPs for carefully crafted code. However, branches stalled the pipeline (modulo special case looping within pipeline); no speculative execution, etc. ... so most codes ran about 5mips (still slightly faster than 3033, which was about 1.5 times 168-3 or 4.5mips). the effort was to duplicate psw and registers to simulate 2-way multiprocessor w/o actually replicating any other hardware (instructions in pipeline would have one bit flag to identify which instruction stream instruction/regs/etc belonged to) ... two 5mip instruction streams utlizing peak 10mips with only modest additional hardware have to settle for 360/195 functional characteristics from bitsavers (very similar to 370/195) http://www.bitsavers.org/pdf/ibm/360/funcChar/A22-6943-0_360-195_funChar.pdf 3081d was supposedly approx. 5mips ... but for some things it ran 20% slower than 3033. 3081k doubled the cache size and was supposedly approx. 7mips ... but for some number of things ran nearly same as on 3033. it isn't until 3090 that you really start to match 195, more than 15 yrs earlier; announce aug1969 http://www-03.ibm.com/ibm/history/exhibits/mainframe/mainframe_PP2195.html 370/195 http://www-03.ibm.com/ibm/history/exhibits/mainframe/mainframe_2423PH3195.html 3090 announce feb1985: http://www-03.ibm.com/ibm/history/exhibits/mainframe/mainframe_PP3090.html big part was the side trip into FS and the disastrous failure (including shutting down lots of 370 development during the FS years). With the failure of FS, there was mad rush to get products back into the 370 pipeline. 3033 started out as 168-3 remapped to 20% faster chips (chips also had 10 times as many circuits/chip, but the extra circuits started out going unused). During 3033 development, some of the critical 168-3 parts was redone to leverage higher circuit/chip density eventually reaching 1.5times 168-3. In parallel with 3033 there was 3081 which was basically the FS 370 emulator ... some amount of details here: http://www.jfsowa.com/computer/memo125.htm from above: The 370 emulator minus the FS microcode was eventually sold in 1980 as as the IBM 3081. The ratio of the amount of circuitry in the 3081 to its performance was significantly worse than other IBM systems of the time; its price/performance ratio wasn't quite so bad because IBM had to cut the price to be competitive. The major competition at the time was from Amdahl Systems -- a company founded by Gene Amdahl, who left IBM shortly before the FS project began, when his plans for the Advanced Computer System (ACS) were killed. The Amdahl machine was indeed superior to the 3081 in price/performance and spectaculary superior in terms of performance compared to the amount of circuitry.] ... snip ... misc. past posts mentioning FS http://www.garlic.com/~lynn/submain.html#futuresys -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: When is performance really an issue? Was: Running an ISPF applicction from one pds
bi...@mainstar.com (Bill Fairchild) writes: > So what is the "exact" location, velocity, and/or mass of one particular > electron? well ... they did manage to recently report that the shape is spherical Electron is surprisingly spherical, say scientists following 10-year study http://www.sciencedaily.com/releases/2011/05/110525131707.htm -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: We list every company in the world that has a mainframe computer
charl...@mcn.org (Charles Mills) writes: > Also is not fiber preferred over copper for secure applications because it > does not act as an antenna? the internal network was larger than the arpanet/internet from just about the beginning until possibly late 85 or early 86. the corporation required encryption on all links leaving corporate premise (use to be all sorts of hassle with gov. agencies when internal network links crossed national boundaries). in the mid-80s, there was claim that internal network had more than half of all link encrypters in the world. misc. past posts mentioning internal network http://www.garlic.com/~lynn/subnetwork.html#internalnet also, for the corporate home terminal program there were special "encryping" pc modems produced. there is folklore about one being installed at senior executive home ... and being an old EE, he used his tongue to check for contacts on the RJ telephone jack ... just as it rang. after that there was requirement that all modems made by the corporation had the RJ jack recessed so that babies and senior executives could get their tongue in them. semi-related to 3737 CTCA channel-extender over T1 (in late 80s) ... recent reference in this thread: http://www.garlic.com/~lynn/2011g.html#75 also in this a.f.c. thread http://www.garlic.com/~lynn/2011g.html#77 I had done channel-extender over T1 in 1980 for STL moving 300 people from IMS group to offsite bldg (parts of it channel over campus T3 Collins digial radio ... aka microwave ... that the company had in the area). I had to do real high-speed ... not the SNA spoofing that the communication group did with the 3737 in late 80s. I ran a project I called high-speed data transport (HSDT) to differentiate from what the communication group was up to ... misc. past posts mentioning HSDT http://www.garlic.com/~lynn/subnetwork.html#hsdt One of the problems was amount of the money I had to pay for T1 link encryptors ... and very difficult finding any that ran faster than T1 ... so got involved in designing something that would run significantly faster, cost significantly less to build and was significantly more secure. a couple recent posts mentioning then discovering there was three kinds of crypto: http://www.garlic.com/~lynn/2011g.html#20 TELSTAR satellite experiment http://www.garlic.com/~lynn/2011g.html#60 Is the magic and romance killed by Windows (and Linux)? -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: We list every company in the world that has a mainframe computer
l...@garlic.com (Anne & Lynn Wheeler) writes: > old '89 email with copy of the spring '85 announcement > http://www.garlic.com/~lynn/2011c.html#890731 re: http://www.garlic.com/~lynn/2011g.html#73 We list every company in the world that has a mainframe computer http://www.garlic.com/~lynn/2011g.html#74 We list every company in the world that has a mainframe computer oops, correction, URL should be http://www.garlic.com/~lynn/2011c.html#email890731 the post: http://www.garlic.com/~lynn/2011c.html#40 Other early NSFNET backbone also has communication group related email from the following day http://www.garlic.com/~lynn/2011c.html#email890801 and a 2nd one from the following day ... i had gotten on the xtp technical advisory board (which the communication group strongly objected to): http://www.garlic.com/~lynn/2011c.html#email890801b where part of XTP specification included reliable multicast which was being used in some environments that might experience an enormous amount of damage but the signals still need to get through. recent post doing channel extender support in 1980 for 300 people/terminals from IMS group that were being moved out of STL to remote bldg (they had tried "remote 3270" and found human factors intolerable) http://www.garlic.com/~lynn/2011g.html#43 My first mainframe experience In 60s, 2701 supported T1 data rates ... and lots of gov. institutions were still using them in the 80s (since the communication group didn't have products w/T1 support). Many customers were moving to products from other vendors (like HYPERChannel) to get T1 and higher speed support. Special T1 RPQ Series/1 Zirpel card was product for gov. accounts where their 2701 were starting to completely fail. Now part of the VTAM problem was that it handled latency on higher speed links, very poorly (even when terrestrial). Part of 3737 was to have a mini-VTAM ... get the transmission from mainframe ... look inside the RU and if possible, immediately tell the host VTAM that it had already arrived at the other end ... and then use (effectively) non-SNA for 3737 to 3737 transmission (lots of VTAM spoofing to effectively compensate for poor VTAM latency handling). from long ago and far away Date: Mon, 6 Jun 88 12:46:05 est From: wheeler Subject: 3737 3737 is the product version of zebra. zebra has a mini-vtam buried in its guts and will only handle connections with a vtam system. 3737 looks like a ctc connection to host vtam. In zebra/3737, it is doing a lot of SNA session management ... it transparently forwards all control RUs to the host vtam at the remote end ... but it does early ACKs for all data RUs (i.e. tells the local host vtam that the data has completed transmission before it has even been sent). The logic/design is somewhat similar to the PVM/S1 support ... but in this case it can only be used with host VTAM system. ... snip ... Date: Wed, 5 Oct 88 15:30:42 EST From: wheeler Subject: 3737 note don't confuse the 3737 with a standard T1 inteface box. 3737 is specifically VTAM only. The 3737 contains a mini-embedded VTAM and can only be directly channel attached to an IBM mainframe and can only be driven by IBM mainframe VTAM system. It is also slow, and what SNA performance it does get is via SNA protocol spoofing (it does early "ACKS" to the local mainframe, as a result packets can be lost w/o any way of notifying higher level protocol layers). ... snip ... -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: We list every company in the world that has a mainframe computer
ps2...@yahoo.com (Ed Gould) writes: > Funny you mentioned that. He was part of the team that looked through > the watergate email (profs) and he was also involved in trying to get > data from some of the drives. He didn't go into a lot of detail but > there was some effort to try and recover overwritten data. I also did > not press him for details. > > One thing he did tell me was that the White House was using fiber > optics for channels. That was decade before IBM made it GA. Something > about not having large cables between rooms so if a bomb hit nothing > could be leaked between rooms. re: http://www.garlic.com/~lynn/2011g.html#73 We list every company in the world that has a mainframe computer i think escon was knocking around POK from the late 70s ... just took a long time to leak out ... in part because many uses would cross datacenter walls ... and communication group "owned" everything that crossed the datacenter walls ... and they thot high-speed was 56kbits; my wife had numerious battles with communication group over such details when she did a stint in POK in charge of loosely-coupled architecture ... misc. past posts http://www.garlic.com/~lynn/submain.html#shareddata Early 80s, there was enormous amount of dark-fiber (i.e. not yet lit) going in all over the place. When new Almaden research bldg opened in the mid-80s, telco put something like six fiber bundles into Almaden bldg. one of rs6000 engineers (in conjunction with rochester) had taken the original escon spec, tweaked to be about ten-percent faster, full-duplex, commodity, more reliable drivers and it was released as SLA. Then in early 90s, we talked him out of doing 800mbit version ... instead to work in fiber-channel-standard (group we had been working with for few years ... had come out of some work originally at LLNL). This became fiber-channel standand. Then some of the POK channel engineers caused a lot of turmoil by layering some unnatural half-duplex stuff on top of base fiber channel standard for FICON (I still have a bunch of old fiber channel standards mailing list from the period). passing reference about jan92 meeting in Ellison's office http://www.garlic.com/~lynn/95.html#13 In HSDT, I was doing a bunch of stuff ... including having custom stuff built on the other side of the pacific. misc. old HSDT email http://www.garlic.com/~lynn/lhwemail.html#hsdt and past posts http://www.garlic.com/~lynn/subnetwork.html#hsdt friday before a trip across the pacific early spring '85, communication group announced a new online discussion group on high-speed with the following definitions: low speed: <9.6kbits medium-speed:19.2kbits high speed: 56kbits very high speed: T1 monday morning on wall of conference room on the other side of pacific: low speed: <20mbits medium speed:100mbits high-speed: 200-300mbits very high speed: 500-600mbits old '89 email with copy of the spring '85 announcement http://www.garlic.com/~lynn/2011c.html#890731 notice that internal network and nearly whole internal corporation ran on vm370 back then ... misc. past posts http://www.garlic.com/~lynn/subnetwork.html#internalnet -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: We list every company in the world that has a mainframe computer
ps2...@yahoo.com (Ed Gould) writes: > I am not sure any numbers you can come up with would tell a story (thats > accurate). I suspect even IBM (in some cases) does not have a clue as to what > is > running on any given machine. Especially in the "sensitive areas" of the > government. I knew of one place that was forbidden to call IBM for software > service. I know IBM has people that have the right clearances (heck I > know/knew > (he has passed away) one that worked in one of the basements of the > Whitehouse > and he couldn't tell me too much what he was working on) He may have told me > too > much just about the existance but we both had clearences at the time. i can imagine that the person scanning the PROFS backup tapes in response to the congressional subpoena (iran/contra/north), required quite a few clearances. more recent ... Hacking of White House E-Mail Affected Diverse Departments http://www.nytimes.com/2011/06/04/technology/04hack.html Gmail Hack Targeted White House http://online.wsj.com/article/SB10001424052702304563104576361863723857124.html a little topic drift in this recent post: http://www.garlic.com/~lynn/2011g.html#61 z/OS System Programmer Needed East Coast -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: What is the current feeling for MVC loop vs. MVCL?
dcrayf...@gmail.com (David Crayford) writes: > http://www.redbooks.ibm.com/redbooks/pdfs/sg246515.pdf > > There is one programming aspect that is relevant, although only > slightly linked to the use of a split cache. For many years, it has > been an axiom among S/360 - S/390 users that assembly language > programmers probably produce faster code than high-level language > compilers. This is no longer true. Processors that use pipelines > (including z800 and z900 machines) require a certain amount of > nonsequential code to obtain the best performance. For example, if an > instruction loads a register and the next instruction uses the > register, we do not have optimum code. This sequence will stall the > pipeline for several processor cycles. (The instructions work > correctly, of course, but they take longer than necessary.) The best > technique is to interleave several unrelated instructions between > loading a register and using the new contents of the register. > > This is not natural, sequential thinking for an assembly programmer, > although he could learn to do it. IBM’s recent S/390 compilers contain > logic to produce this sort of optimized code. re: http://www.garlic.com/~lynn/2011g.html#67 What is the current feeling for MVC loop vs. MVCL? which makes highly optimized code start to look more like old-time horizontal microcoding (high-end pok machines, 3830 controller, etc) ... where the programmer was dealing in concurrent operations with various latencies ... and trying to maximize overlapped operation. -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: z/OS System Programmer Needed East Coast
et...@tulsagrammer.com (Eric Chevalier) writes: > Why do the letters "N S A" keep popping into my mind??? :-) from long ago and far away: http://www.nsa.gov/research/selinux/list-archive/0409/8362.shtml one of the "benefits" of cp67 and then vm370 was complete source as well as tradition of doing maintenance in source (customer could rebuild exact duplicate of production system from source). there is folklore in the 80s about a request for something similar for MVS ... the exact source corresponding to particular production system ... supposedly after spending millions on the investigation ... the company decided that it wouldn't be practical. -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: What is the current feeling for MVC loop vs. MVCL?
re: http://www.garlic.com/~lynn/2011g.html#57 What is the current feeling for MVC loop vs. MVCL? other recent gcc reference: http://www.garlic.com/~lynn/2011g.html#50 My first mainframe experience ... and recent reference to out-of-order pipeline introduced http://www.garlic.com/~lynn/2011f.html#46 At least two decades back, some gurus predicted that mainframes would disappear in future and it still has not happened mentions that introduction of out-of-order in most recent mainframe accounts for significant part of throughput increase (although it has been in other architectures for decades). decades ago, out-of-order was given as major rise of advanced compilers for high-throughput optimization ... since internal machine processing was getting a lot more complex with various kinds of instruction interdependencies and complex dataflow ... becoming harder and harder to address with manual effort. -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: What is the current feeling for MVC loop vs. MVCL?
john_w_gilm...@msn.com (john gilmore) writes: > These optimizations are also devised by groups whose full-time job is > to optimize code skeletons that are used stereotypically in > compiler-generated code; and these groups inevitably come to have a > vested interest in cleverness, i.e., non-standard, less than obvious > ways of doing things. more recent state-of-the-art ... is to build a model of the hardware & instruction operation ... and have code that selects instruction combinations based on specified cycles (or some other criteria) ... that code is now finding non-standard, possibly non-obvious, instruction sequences (also makes it easier to do large number of backends across variety of different machine architectures). Part of machine model (for execution) includes things like out-of-order execution dependencies. long ago and far away, early cp67 (virtual machine precursor to vm370, ran on 360/67) shipped with virtual address tables initialized pointing to a special "zeros" page on disk. I changed that to indicate a "zeros" page and just cleared the storage to zeros. Common operation of the period was to use (multiple) overlapping MVC. I did implementation that saved registers, zero'ed ten registers and did BXLE STM loop for those ten registers (significantly faster than overlapping MVC ... on 360/67). GCC 4.6 http://gcc.gnu.org/gcc-4.6/changes.html from above: S/390, zSeries and System z9/z10, IBM zEnterprise z196 Support for the zEnterprise z196 processor has been added. When using the -march=z196 option, the compiler will generate code making use of the following instruction facilities: Conditional load/store Distinct-operands Floating-point-extension Interlocked-access Population-count The -mtune=z196 option avoids the compare and branch instructions as well as the load address instruction with an index register as much as possible and performs instruction scheduling appropriate for the new out-of-order pipeline architecture. When using the -m31 -mzarch options the generated code still conforms to the 32-bit ABI but uses the general purpose registers as 64-bit registers internally. This requires a Linux kernel saving the whole 64-bit registers when doing a context switch. Kernels providing that feature indicate that by the 'highgprs' string in /proc/cpuinfo. The SSA loop prefetching pass is enabled when using -O3. ... snip ... -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: My first mainframe experience
ps2...@yahoo.com (Ed Gould) writes: > Hehe Gerhard, obviously a type that of course should have been 25 years ago. > I have no experiance on LINUX but would guess it does not come with a FORTRAN > compiler. > My memory is iffy here but IIRC both (three) source programs had to be babied > to > work in the FORTRAN G1 that we had. I think waterloo had a FORTRAN compiler > but > we were semi afraid that they wouldn't be to good at support. Can anyone > confirm > the Waterloo Fortran? mentions careful re-ordering of stage-2 sysgen that resulting improving student job thruput by nearly factor of 3 times (careful arm seek positioning) http://www.garlic.com/~lynn/2011g.html#44 My first mainframe experience student jobs had run approx. second elapsed time under tape-to-tape ibsys on 709. moving student jobs to 360/67 (running as 360/65) with MFT ... was well over a minute (3 step fortran g compile, link-edit and go). Adding HASP got it down under a minute per student job. old post with part of presentation i gave at aug68 share meeting http://www.garlic.com/~lynn/94.html#18 had gotten student jobs to little over 11seconds (with careful ordering of files & pds members). other trivia ... as part of recrafting stage2 sysgen also allowed me to do it in production job stream. it wasn't until waterloo watfor that student jobs got back down to 709 IBSYS thruput. watfor ran as its own monitor ... taking card tray of large number of student jobs (as single job step) ... compiling each student job into "in-memory" allocated storage area, executing it, and then doing the next student job. supposedly watfor could compile something like 20,000 "cards" per minute on 360/65(with actual execution of typical student jobs being minimal). watfor/watfiv, etc (also mentions later work in mid-80s for running in ibm/pc): http://en.wikipedia.org/wiki/WATFIV common on linux systems is GCC ... which comes with a large number of different (language) front-ends and backends ... wiki reference: http://en.wikipedia.org/wiki/GNU_Compiler_Collection from above: Originally named the GNU C Compiler, because it only handled the C programming language, GCC 1.0 was released in 1987, and the compiler was extended to compile C++ in December of that year.[1] Front ends were later developed for Fortran, Pascal, Objective-C, Java, and Ada, among others.[7] ... snip ... also from above: The standard compiler release 4.6 includes front ends for C (gcc), C++ (g++), Java (gcj), Ada (GNAT), Objective-C (gobjc), Objective-C++ (gobjc++) and Fortran (gfortran).[16] Also available, but not in standard are Go (gccgo), Modula-2, Modula-3, Pascal (gpc), PL/I, D (gdc), Mercury, and VHDL (ghdl).[17] A popular parallel language extension, OpenMP, is also supported. The Fortran front end was g77 before version 4.0, which only supports FORTRAN 77. In newer versions, g77 is dropped in favor of the new gfortran front end that supports Fortran 95 and parts of Fortran 2003 as well.[18] As the later Fortran standards incorporate the F77 standard, standards-compliant F77 code is also standards-compliant F90/95 code, and so can be compiled without trouble in gfortran. ... snip ... -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: My first mainframe experience
lindy.mayfi...@ssf.sas.com (Lindy Mayfield) writes: > I seem to recall one OS had a command to crash the computer. Kill > command or some such. Took the fun out of everything I guess, or I > perhaps that was their intention. internally, in the 70s&80s, large percentage of systems ran vm ... that had constant system activity monitoring ... conventions dating back to mid-60s with cp40 and cp67. as a result, there built up quite a large body of information about system configurations and workload profiles. misc. past posts mentioning science center http://www.garlic.com/~lynn/subtopic.html#545tech as part of various performance work at the science center (some of which eventually matured into capacity planning) ... built automated logon at system startup to initialize synthetic workloads for benchmarking purposes. part of the performancing modeling work at the science center was analytical model done in APL. This was eventually made available on HONE (online virtual machine worldwide sales&marketing support) as the "performance predictor" ... where sales & SEs could characterize customer configuration and workload and then ask "what if" questions about what would happen if hardware configuration &/or workload was changed. misc. past posts mentioning HONE http://www.garlic.com/~lynn/subtopic.html#hone i used the autolog startup & command for extensive benchmarking leading up to release of my (dynamic adaptive) resource manager. part of the process could include automatically building a new kernel, crashing (the current system) & rebooting the new kernel, running benchmark ... and then repeating the process automatically thousands of times. Final sequence for release of my resource manager invovled 2000 automated benchmarks that took three months elapsed time to run. For this final sequence, the configuration and workload profiles were preselected (as representive of all the internal & customer systems that had information on) for the first 1000 benchmarks. For the final 1000 benchmarks a specially modified version of the "performance predictor" was used to select configuration and workload profiles, predict the result, run the benchmark, compare the predicted and benchmark results, and then repeat process. misc. past posts mentioning performance modeling and benchmarking work from the 70s http://www.garlic.com/~lynn/submain.html#bench a couple old emails about porting bunch of cp67 code to vm370 and then supporting "csc/vm" system for internal distribution: http://www.garlic.com/~lynn/2006v.html#email731212 http://www.garlic.com/~lynn/2006w.html#email750102 http://www.garlic.com/~lynn/2006w.html#email750430 above mentions autolog command that I had originally done for the benchmarking process. cp67 already had automatic kernel reboot after system crash ... but it came up (automatically) just enabled for (manual) logins. As more and more services were done as service virtual machines (currently sometimes referred to as "virtual appliances"), just having system back up for login wasn't sufficient ... all the "service virtual machines" had to be brought up also. the work I had done for automated benchmark increasingly became used for automated restart of the service virtual machines. the above also mentions SPM command which was used for various automated operator mechanisms ... i.e. a (disconnected service) virtual machine could have anything that would show on physical terminal ... available to software (it was also used for multi-user spacewar implementation) ... SPM had originally been done for CP67 at the Pisa science center (and converted to vm370 at one of the POK datacenters). recent posts in this thread: http://www.garlic.com/~lynn/2011g.html#41 My first mainframe experience http://www.garlic.com/~lynn/2011g.html#43 My first mainframe experience http://www.garlic.com/~lynn/2011g.html#44 My first mainframe experience http://www.garlic.com/~lynn/2011g.html#45 My first mainframe experience adventure had been done in fortran on pdp10 ... and was available on the stanford (pdp10) system. http://www.rickadams.org/adventure/e_downloads.html my impression was somebody at Tymshare (provider of commercial online vm370 timesharing services) had copied it (fortran version) to Tymshare pdp10 and then got in running on Tymshare vm370/cms system. Tymshare also made their system available to SHARE for online computer conferencing (as VMSHARE) starting in Aug76: http://vm.marist.edu/~vmshare/ triva ... Stanford, HONE datacenter and Tymshare were all within couple miles of each other. I set up process for Tymshare to mail me monthly tapes of everything on VMSHARE (later included PCSHARE) and I would make it available on the internal network hosted on number of internal systems (including HONE). Adventure was also ported to stanford orvyl system ... aka a number of univ. had been sold 360/67 to run IBM's tss/360 ... when tss/360 was floundering, many univ. just used the machine as 360/65 ... however, Uni
Re: My first mainframe experience
gerh...@valley.net (Gerhard Postpischil) writes:
> The 2260s were attached to a 2848 control unit. I worked at ADR when
> they were announced, and a couple of us used them for playing games
> (e.g., a battleship game by Dave McBride). {partly as a result of our
> experience, we won a CIA contract for interactive text scanning that
> seems horribly antiquated by today's standards.
>
> If you started on a 360, you're a newbie Some of us on the list
> worked with 70x and 709x "mainframes."
re:
http://www.garlic.com/~lynn/2011g.html#41 My first mainframe experience
http://www.garlic.com/~lynn/2011g.html#43 My first mainframe experience
http://www.garlic.com/~lynn/2011g.html#44 My first mainframe experience
the univ. had 2250m1 (direct channel attach) and I hacked the cms editor
to use it (early fullscreen editor, borrowing 2250m1 software library
that lincoln labs had done for cms).
later at the science center, there was a 2250m4 (aka 1130+2250 combo ...
the 2250m4, including 1130 ... was about the same price as the 2250m1).
somebody had ported spacewar to the 2250m4 ... where the keyboard was
split in half ... with keys on two sides of keyboard used for controls
for two-person game. i would bring my kids in on the weekends and they
would play spacewar on the machine.
original on pdp1 (before porting to 1130/2250):
http://en.wikipedia.org/wiki/Spacewar!
misc. past posts mentioning science center
http://www.garlic.com/~lynn/subtopic.html#545tech
a decade or so later, there was a distributed multiuser cms spacewar
game done by the author of rexx (played on 3270). somebody would have
spacewar controller/server running ... and users could run clients on
their own cms ... it used spm for inter-virtualmachine communication
with the spacewar server (would worked with the server on the same
machine or through the internal network from other machines around the
company).
then some number of people wrote "robot" spacewar clients that would
make moves much faster and beat human players. the spacewar server was
then modified to dramatically increase energy use as the interval
between client operations decreased (attempting to somewhat level the
field between robot and human players).
--
virtualization experience starting Jan1968, online at home since Mar1970
--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO
Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: My first mainframe experience
jim_peter...@homedepot.com (Petersen, Jim) writes: > How about 2260's was a terminal control unit for terminals which only > had 12 lines by 80 Cut my teeth on 360/65 and a 360/50 and a 360/40 > and they had a 360/20 down at one of our sites for RJE. re: http://www.garlic.com/~lynn/2011g.html#41 http://www.garlic.com/~lynn/2011g.html#42 http://www.garlic.com/~lynn/2011g.html#43 not display ... but 2741&TTY terminals. As undergraduate, I had been doing a whole lot of work with OS/360 & HASP ... prior to getting involved with (virtual machine) cp67. I would tear apart stage2 output from stage1 sysgen and re-organize all the move/copy steps & statements to careful order files and PDS members. For typical univ. student jobstream this got nearly three times thruput (with hasp, each student job as 3step fortran compile, link & go ... before installing watfor for student jobs). initial cp67 installed at the univ. had support for 2741 & 1050s. The univ. had some number of TTY/ascii terminals so I decided to add TTY support to CP67. CP67 2741&1050 support did automatic terminal identification ... playing dynamic games with 270x controller SAD command (would change which line-scanner was associated with which line/port). I tried to put in TTY support so it would do automatic terminal identification consistently. It would work for leased lines ... but I wanted to have single dialup number that could be used for all terminals (common "hunt group" and pool of lines). Turns out it wouldn't quite work since 2702 took shortcut and hardwired the line speed to each port. this was somewhat the justification for the univ. starting clone controller effort ... reverse engineering the channel interface and building channel interface board for Interdata/3 (programmed to emulate 270x) ... and being able to do both dynamic line-speed and terminal type identification. later, four of us got written up being blamed for some part of clone controller business. http://www.garlic.com/~lynn/subtopic.html#360pcm later, P/E bought Interdata and the box was sold for many years under the perkin/elmer logo. In the late 90s, I ran into such a box in large east coast datacenter handling large percentage of merchant dial-up payment card swipe cards in the us (ran into former P/E salesman that said he didn't think they ever changed the channel interface board design) in any case, I also decided to hack 2741 & TTY terminal support into side of HASP (removing 2780 support to cut down real storage footprint). I re-implemented a conversational editor from scratch ... with CMS editor syntax ... for a form of CRJE (and I considered much better than early TSO from the period). -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: My first mainframe experience
ps2...@yahoo.com (Ed Gould) writes: > Back in the 70's & 80's the place I worked had 1500 (or so) local 3270's off > of > a 168MP. > We were truly at the UCB # limit for MVS. We were forever having to do > sysgens > as our VP was a hungry for drives. The conversion to 3350's did save us a bit. > But what truly helped us was the 3274L's (1 UCB and 32 address's) (SNA local > controller). > Our monitoring of channel's we did not tend to see much busies on the byte > channel's even with the 3705 we rarely saw anything that concerned us (say > more > than 10 percent busy). BTW the online CICS application was a really big > fullscreen transfer user. > I am not sure where the chatty part you were talking about but we never saw > it > and the people that were entering the data were no slouches for entering > lot's > of data. re: http://www.garlic.com/~lynn/2011g.html#41 & unnrelated old CICS reference: http://www.garlic.com/~lynn/2011g.html#42 interactive computing tended to have a lot more interactions that pure data entry. 3270s in general were half-duplex ... so from the time enter was hit until it was safe to type again ... increased with 3274 ... because so much electronics had been moved out of the terminal and back to the controller. the half-duplex problem also showed up if the system as doing something asynchronously while typing ... if system went to write to the screen while key was being hit, the keyboard would lock and then person would need to stop and hit reset (again horrible human factors). the reference http://www.garlic.com/~lynn/2001m.html#19 3270 protocol gave comparison timing between 3272/3277 and 3274/3278 for just internal hardware part of the controller ... base 3272/3277 hardware processing was .086 seconds ... with 90percentile trivial interactive CMS response of .11sec ... that gave effective human perceived response of .196 seconds. base 3274/3278 hardware processing was .530 seconds. The corporation had started doing a lot in the area programmer productivity and human factors ... establishing quarter second response time as a goal. The reference numbers were from a internal ibm study that showed that it was impossible to meet the objectives with direct channel attached 3274 controllers. going to SNA made the latencies and delays much worse ... and going to any kind of remote made human interactive intolerable. That was what initially prompted the HYPERChannel channel extender for the STL development lab. STL was bursting at the seams and 300 people from the IMS group were being moved to off-site building. They had done some experiments with remote 3270 and found the human factors totally unacceptable. The channel extender from the offsite building back to STL datacenter, allowed the local channel attached 3270 controllers to be placed at the remote building and human response and interactive characteristics appeared as if they werer still in the STL bldg. As it turned out, getting the direct channel 3270 controllers off the real channels had a side-benefit of increasing overall system throughput by 10-15% with the electronics in the head of 3277 it was possible to further improve the human factors ... including eliminating the half-duplex keyboard locking ... when there is normal interactive operation going on concurrently between system and user (user potentially constantly typing while the system might do something that would asynchronously update part of the screen). Open the 3277 keyboard and little soldering ... and could adjust the key repeat delay and the key repeat rate ... to a much more human acceptable rate. Also got a vendor to build a small fifo box ... unplug the keyboard from the 3277 head, plug the box into the 3277 head and plug the 3277 keyboard into the fifo box. This provided a keystroke buffer to eliminate keyboard getting locked if key was being pressed same time screen was getting something written. in the 3274/3278 ... with all the electronics moved back into the controller, it was no longer possible to perform these human factor hacks. also with much of the electronics back in the controller ... there was enormous increase in protocol chatter over coax cable between what was going on in the 3278 terminal head and the electronics back in the controller. later with terminal emulation ... is was possible to program the PC for human factors ... compensating for the 3270 human factor characteristics. However, the enormous increase in protocal chatter over coax cable drastically reduced upload/download throughput for 3274/3278 terminal emulation ... compared to what could get from 3272/3277 terminal emulation (since 3274/3278 had both lot more extranous protocol chatter as well as significantly more handshaking operation latencies doing any data movement between controller and head). the terminal emulation paradigm shows up later with the controllers supporting token-ring and PCs with T/R adapters. The PC/RT workstation (with AT ISA bus) ha
Re: z/OS SYSLOG to UNIX syslog daemon?
rfocht...@ync.net (Rick Fochtman) writes: > Rumor had it at one time: the MSS cartridges contained all the > left-over tape from the 2321 strips. Seems that the tape was > over-stocked 'cuz the 2321 never took off like someone hoped it would. re: http://www.garlic.com/~lynn/2011g.html#36 2321 capacity was 400mbyte. http://en.wikipedia.org/wiki/IBM_2321_Data_Cell length of 2321 strip was height of a cell http://www.columbia.edu/acis/history/datacell.html ibm 2321 archives: http://www-03.ibm.com/ibm/history/exhibits/storage/storage_2321.html 3850 cartridge was about 50mbytes http://www-03.ibm.com/ibm/history/exhibits/storage/storage_3850.html http://www-03.ibm.com/ibm/history/exhibits/attic3/attic3_019.html ... the smallest 3850 had 706 cartidges or 35B bytes and the largest held 472B bytes. more 3850 http://www.columbia.edu/acis/history/mss.html ... 2000 cartidges of 50MB each, it was used to hold the entire 1980 USA Census and was made available to users of Columbia's IBM mainframe single 3850 likely held more than total of all the 2321s strips made. when I was undergraduate, the univ. library got an ONR grant to do online catalog ... part of the money was used to get a 2321. the project was also selected to betatest for the original CICS product ... and I got tasked to support/debug that CICS installation. misc. past posts mentioning bdam &/or cics http://www.garlic.com/~lynn/submain.html#cics -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: My first mainframe experience
chrisma...@belgacom.net (Chris Mason) writes: > http://publibz.boulder.ibm.com/cgi-bin/bookmgr_OS390/BOOKS/admg1a05/6.3.4 > > Table 8 has all the numbers. > > 3174 was a 3270 control unit. > > 4341 was a processor, a "mainframe". 3272 was controller for 3277 3274 was introduced as controller for 3278. besides other changes from 3272/3277 to 3274/3278, a lot of the electronics were moved out of the terminal head and back into the 3274 controller reducing manufacturing costs and drastically increasing communication chatter over the coax (and reducing response). we complained about the significant worse human factors characteristics for 3274 controller. eventually we got a response that 3274/3278 wasn't designed for interactive computing ... but for data entry (basically updated keypunch technology). past post with old reference to 3272/3277 & 3274/3278 comparison http://www.garlic.com/~lynn/2001m.html#19 3270 protocol 3274 was "slow" in other ways ... it had very high "channel busy" overhead doing command processing. I did a project for STL (now SVL) writting support for HYPERChannel channel extender ... allowing local 3274 controlers to moved to offsite building. As a side-effect of moving real 3274 off the channels ... being replaced with HYPERChannel boxes, significantly reducing channel busy for doing the same 3274 operations ... increased overall system thruput by 10-15%. ... misc. past posts mentioning various efforts ... some involving HYPERChannel http://www.garlic.com/~lynn/subnetwork.html#hsdt later in terminal emulation in ibm/pc ... a 3277 terminal emulation card had much better upload/download thruput compared to 3278 terminal emulation card (because of design with the electronics back in the controller ... requiring significant increase coax protocol chatter ... cutting effective upload/download thruput). some old references about terminal emulation thruput http://www.garlic.com/~lynn/2005r.html#17 Intel strikes back with a parallel x86 design http://www.garlic.com/~lynn/2007r.html#10 IBM System/3 & 3277-1 http://www.garlic.com/~lynn/2010m.html#80 3270 Emulator Software other posts with references to terminal emulation http://www.garlic.com/~lynn/subnetwork.html#terminal 4341 was "mid-range" done by endicott. some number of old emails related to 4341 http://www.garlic.com/~lynn/lhwemail.html#4341 POK was surprised that 4341 was beating 3031. in the wake of failure of FS effort, there was mad rush to get products back into 370 product pipeline ... some part of that was 303x which was largely warmed over 370; 3031 was warmed over 370/158-3. clusters of 4341s had higher thruput, were lower cost and required significant reduced physical resources compared to 3033 (there is folklore about internal dirty tricks that cut in half the allocation of critical 4341 manufacturing component) 4341 increased performance, reduced costs, reduced physical requirements ... and there was big explosion in the numbers sold. Many corporations were facing running out of physical space in datacenters ... and it was possible to place 43xx machines out in dept. supply rooms and conference rooms. Large corporations had orders for several hundred at a time that went all around the corporation ... the leading edge of the distributed computing wave. internally, so many were going into dept. conference rooms, that conference rooms started to become scarce corporate resource. the explosion in number of 43xx machines internally helped spike the number of internal network nodes: http://www.garlic.com/~lynn/subnetwork.html#internalnet hitting 1000 nodes summer of 1983 ... old reference: http://www.garlic.com/~lynn/99.html#112 list of corporate sites with new network nodes added during 1983 (very large percentage being vm/43xx machines): http://www.garlic.com/~lynn/2006k.html#8 old post with picture of 1000th node desk ornament http://www.garlic.com/~lynn/2006k.html#43 above has copy of old email on the subject http://www.garlic.com/~lynn/2006k.html#email830422 -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: z/OS SYSLOG to UNIX syslog daemon?
st...@trainersfriend.com (Steve Comstock) writes: > Ahhh! The memorable Mass Storage System. Pluck, shuck, and play. > ISTR it was the 3950, but I could be wrong. I wrote training for > it back when I was with IBM; even had it translated into German. > But I can't find the books now (this was 1974-75 after all). close, 3850 http://www-03.ibm.com/ibm/history/exhibits/storage/storage_3850.html -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: Running z/OS On Your Laptop
poodles...@sbcglobal.net (Dan Skomsky, PSTI) writes: > It is obvious IBM has a different direction they are pursuing. I have > been re-hosting CICS applications onto Windows platforms for over ten > years. From what I have seen, all the smaller accounts have been > converted with only the "Big Boys" left. But even they are wavering > today. It is only a matter of time... i remember Amdahl giving a talk at MIT in the early 70s ... and somebody asked him what justification did he use to get investment in his new clone processor company. His reply was that IBM customers had already invested enormous amount on 360/370 software and even if IBM were to completely walk away from 370 (might be considered a veiled reference to Future System effort which was completely different from 370 and in fact was killing off potentially competitive internal 370 projects in progress), that software base was sufficient to keep him in business through the end of the century. misc. past posts mentioning future system http://www.garlic.com/~lynn/submain.html#futuresys The Future System period is credited with giving the clone processors a foothold in the market ... having killed off internal 370 competitive efforts, when Future System failed, there was a mad rush to get stuff back into the 370 product pipelines. I had continued to do 370 stuff during the period ... and the mad rush likely contributed to decision to release various of things I had been doing. In the 23jun69 unbundling announcement, there was start to charge for application software ... but they managed to make the case that kernel software should still be free. However, in the aftermath of Future System failure and clone processors in the market place, there was a decision to transition to (also) charge for kernel software. One of my things that was being released was my (dynamic adaptive) resource manager ... and it was selected to be initial guinea pig for kernel software charging ... and I got to spend a lot of time with legal and business people regarding kernel software charging policies. misc. past posts mentioning unbundling http://www.garlic.com/~lynn/submain.html#unbundle A decade later, a senior disk engineer got a talk scheduled at the annual, world-wide, internal communication group talk and opened it with statement that the communication group was going to be responsible for the demise of the disk division. The issue was that the communication group had a stranglehold on the datacenters and large amount of mainframe data was starting to flee to more distributed computing friendly platforms. Many of the "big boys" spent billions on "re-engineering" projects (moving off mainframes) in the 90s that failed. many of them were using technology that looked marvelous in demos but failed miserably to scaleup (and may have worked for smaller operations). at least a couple years ago those failures (in the 90s) were still damping the appetite to try it again soon (somewhat analogous to the dark shadow that the FS failure cast over IBM for decades). -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: SV: USS vs USS
mike.a.sch...@gmail.com (Mike Schwab) writes: > http://en.wikipedia.org/wiki/IBM_AIX > IBM wrote TSS/370 in 1980 then VM/IX then AIX/370 in 1988 then AIX/ESA > until 1999 when it merged into MVS/ESA Open Edition. tss/360 was done in the 60s (official system for 360/67) ... was decommited and lived on as small special project. some of the single-level-store (paged-mapped filesystem) ideas were picked up for (failed) future system effort ... misc. past posts mentioning future system http://www.garlic.com/~lynn/submain.html#futuresys folklore is that after demise of future system, some of the participants retreated to rochester and did s/38 ... which then morphs into as/400 in the 80s, tss/370 got something of a new life ... as base for special bid mainframe unix for AT&T ... stripped down tss/370 kernel (SSUP) with AT&T doing unix interfaces to the SSUP kernel interface (in some sense this is somewhat analogous to USS for MVS). this was competing with Amdahl's GOLD/UTS unix internally inside AT&T. AIX/370 (in conjunction with AIX/386) was done by palo alto group using the unix-like LOCUS done at UCLA. This was similar but different from the unix-like MACH done at CMU ... which was used by a number of vendors including NeXT and morphs into current Apple operating system after Jobs returns to Apple. AIX/370 morphs into AIX/ESA. The "argument" for (Amdahl) UTS under vm370, aix/370 under vm370, tss/370 ssup, and vm/ix (on vm370) was that the cost to add mainframe RAS&erep to unix was several times larger than the base, direct, straight-forward unix port (running under vm370 &/or tss/370 leveraged the already existing ras&erep support w/o having to re-implement directly in unix). This was aggrevated by field service stand that it wouldn't service/support machines that lacked mainframe RAS&erep. I ran internal advanced technology conference in '82 ... and some of the presentation were about VM/IX implementation ... old post reference: http://www.garlic.com/~lynn/96.html#4a Palo Alto group had also been working with Berkeley to port their unix-like BSD to mainframe ... but they got redirected instead doing a PC/RT port ... released from ACIS as "AOS" ... as an alternative UNIX to the "official" AIXV2. The wiki page says much of the AIX v2 kernel was written in PL/I. The issue was that the original "displaywriter" was based on ROMP, cp.r, and PL.8 (sort of pli subset). Redirected to the unix workstation market required unix&C (all being done by the company that had done pc/ix and had been involved in vm/ix). For the internal people, a project called VRM was devised ... a sort of abstract virtual machine layer ... to be done by the internal employees trained in pl.8. The claim was that the combination VRM plus unix port to VRM ... could be done in shorter time and less resources than unix port directly to ROMP hardware. The exact opposite was shown when the palo alto group did the BSD port direct to ROMP hardware (for "AOS"). VRM+unix drastically increased original/total development costs, life-cycle support costs and complicated things like new device drivers (since both non-standard unix/c device driver to VRM interface as well as VRM/pl.8 device driver had to be developed & supported). misc. past posts mentioning 801, romp, rios, pc/rt, aixv2, aixv3, power, rs/6000, etc http://www.garlic.com/~lynn/subtopic.html#801 misc. old email mentioning 801 http://www.garlic.com/~lynn/lhwemail.html#801 Besides various other issues, the AIX wiki page skips over the whole generation of OSF http://en.wikipedia.org/wiki/Open_Software_Foundation and the "unix wars" http://en.wikipedia.org/wiki/UNIX_wars Project Monterey http://en.wikipedia.org/wiki/Project_Monterey skips over the whole cluster scaleup after IBM bought Sequent and support for Sequent's 256-way SCI-based Numa-Q. Recent posts in (linkedin) "Greater IBM" (current & former IBMer) discussion http://www.garlic.com/~lynn/2011d.html#7 IBM Watson's Ancestors: A Look at Supercomputers of the Past the sequent wiki ... mentioned in the above post ... used to be somewhat more caustic about sequent being dropped shortly after the sponsoring executive retired: http://en.wikipedia.org/wiki/Sequent_Computer_Systems as noted in the "Greater IBM" post ... at one time, IBM had been providing quite a bit of funding for Chen's Supercomputer ... Sequent later acquires Chen Supercomputer and Chen becomes CTO at Sequent ... we do some consulting for Chen (before Sequent purchase by IBM). Part of the speculation for IBM's purchase of Sequent was that Sequent was major platform for some of the IBM mainframe simulator products. much of the "posix" (aka unix) support in MVS during the first half of the 90s was sponsored by the head of the disk division software group. in the late 80s, a senior disk engineer got a talk scheduled at the internal, annual, world-wide communication group conference ... and opened the talk with the statement that the communication group was goin
Re: TSO Profile NUM and PACK
re: http://www.garlic.com/~lynn/subtopic.html#80 TSO Profile NUM and PACK Note: UNIX traces some of its history back to CTSS by way of MULTICS done on 5th flr of 545 tech sq. VM370/CMS also traces history back to CTSS by way of CP67/CMS and CP40/CMS done (at science center) on 4th flr of 545 tech sq. misc. past posts mentioning science center http://www.garlic.com/~lynn/subtopic.html#545tech example is UNIX (document formating) runoff/roff looks very much like CTSS "runoff". original CMS (document formating) "script" also looked very much like CTSS "runoff" ... this was before GML was invented at the science center in 1969 and GML tag processing added to CMS "script". misc. past posts mentioning GML &/or SGML http://www.garlic.com/~lynn/submain.html#sgml CTSS reference: http://www.multicians.org/thvv/7094.html Discusses some of CTSS relationship to CP/CMS, MULTICS, and UNIX (mentions that TSO is in no way related): http://en.wikipedia.org/wiki/Compatible_Time-Sharing_System Discusses some of CP/CMS relationship to CTSS http://en.wikipedia.org/wiki/History_of_CP/CMS Multics reference http://www.multicians.org/general.html Unix and Multics reference http://www.multicians.org/unix.html -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: TSO Profile NUM and PACK
paulgboul...@aim.com (Paul Gilmartin) writes: > I've long wondered, if sequence numbers are so valuable, why > haven't they spread outside the progeny of unit record systems? cms multi-level source update infrastructure relied on sequence numbers ... started out with cp67/cms and the cms "update" command which applied a single update file ... used control commands that inserted, replaced, deleted based on sequence numbers of the source file ... output file typically treated as temporary for compile/assemble. at the univ., I was making so many cp67/cms source changes that I created a pre-processor for update ... that added extra field to the insert&replace control statements (aka "$") that would generate sequence numbers of the new lines (otherwise they had to be manually entered/typed). later in early 70s ... there was large "exec" wrapper that supported multiple updates in specified sequence. there was a joint development effort with endicott that added 370 virtual machine simulation to cp67 (that ran on 360/67) ... including new instructions and virtual memory support that had several differences from 360/67. There was "base" set of local enhancements to cp67 ... referred to as the "L" updates ... then could apply the "H" updates to provide option for 370 virtual machines (in addition to 360 virtual machines), and then could apply the "I" updates which modified cp67 to run on 370 machine (rather than 360/67). "cp67i" was running regularly in 370 virtual machine for a year before the first 370 engineering machine with virtual memory hardware support was operational (a 370/145 in endicott) ... in fact, booting "cp67i" on the engineering machine was part of early validation test for the hardware. turns out boot failed ... because of "errors" in the hardware implementation (cp67i was quickly patched to correspond with incorrect hardware ... and then booted succesfully). By the time of vm370/cms, the multi-level update conventions ... and incorporated into CMS update command (eliminating need for the exec wapper) and various editors. Editors were also modified to have option to generate edit session saved changes as an incremental update file (as opposed to replacing the original file with the changes). There is folklore about HASP/JES2 group had moved to cms source development process ... which resulted in various kinds of problems for exporting into standard POK product release environment. In the mid-80s, Melinda had requested anybody with a copy of the original cp67/cms multi-level update implementation. It turns out that I had complete set on archived tapes in the Almaden datacenter tape library. Her request was timely since a couple months later the Almaden datacenter had an operations problem with mounting random tapes as scratch (destroying large number of tapes, including ones with my archived info from the 70s ... in some cases multiple tapes with replicated copies ... including those with large amount of cp67/cms files). old email exchange with Melinda http://www.garlic.com/~lynn/2006w.html#email850906 http://www.garlic.com/~lynn/2006w.html#email850906b http://www.garlic.com/~lynn/2006w.html#email850908 Melinda's home page has moved: http://web.me.com/melinda.varian/Site/Melinda_Varians_Home_Page.html I had done kindle conversion of her history ... which she now has up: http://web.me.com/melinda.varian/Site/Melinda_Varians_Home_Page_files/neuvm.azw cms update command reference: http://publib.boulder.ibm.com/infocenter/zos/v1r10/topic/com.ibm.zos.r10.asmk200/ap5cms8.htm xedit cms command reference (including mention of update option support) http://publib.boulder.ibm.com/infocenter/zvm/v5r4/topic/com.ibm.zvm.v54.dmsb6/xco.htm note that univ source update uses "down-dates" ... i.e. the "current" source file includes all changes ... but there are history files that allows changes to be "regressed" to earlier versions. the cms "up-dates" process would freeze the original source (for some period of time) and have sequence of incremental source updates that would be applied in sequence to arrive at most up-to-date file to be compiled/assembled. -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: Overloaded acronyms
at one point there was almost PCO (personal computing option) ... sort of TSO for VS/1 ... however it was eventually pointed out that PCO was also initials for political party in europe ... and PCO morphed into VS/PC. there was one plan to have VS/1 machines already preloaded with vm/cms (sort of like early flavor of LPARs) ... and using CMS as the interactive component. PCO was being positioned as an alternative. The PCO group had a "simulator" showing PCO performance something like ten times that of vm/cms ... their simulation group would "run" some number of "benchmarks" ... and then the vm/cms group were asked to perform similar (real) benchmarks (taking up a significant percentage of all vm/cms resources on the benchmarks ... taken away from doing actual development). When PCO was finally operational ... it turned out to be slower than vm/cms (but they managed to waste a significant percentage of vm/cms development resources on the fictitious benchmarks) various internal politics blocks the strategy to preload vm/cms on every mid-range machine. then in the wake of the death of Future System effort ... the MVS/XA effort managed to convince corporate to completely kill-off vm/cms (shutting down the development group and moving everybody to POK to support MVS/XA ... with claim that they wouldn't otherwise make MVS/XA ship schedule). Endicott eventually managed to save the vm/cms product mission ... but had to reconstitute a development group from scratch. -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: Mixing Auth and Non-Auth Modules
jeff.ho...@fiserv.com (Jeff Holst) writes: > I think that when I was later in an MVS shop, our auditors used that same > playbook, but I also think that they read slowly, as they seemed to find one > new thing in the book each year. when corporate came in for audit of SJR datacenter in the early 80s ... there was big dustup with the auditors over demo programs (aka "games") ... which should be eliminated from every system ... as not a "business use". Corporate had gone thru a cycle where the 3270 logon screen had "For Business Use Only" added. We managed to have that changed to "For Management Approved Use Only" ... where games actually served a very useful purpose ... giving people exposure to significantly better human interface experience ... that was hardly common in the period. We also used the argument that eliminating public games ... would just drive them underground with each person having private disguised versions. 6670s (copier3 with computer interface added) were appearing in every departmental area for distributed computer output. the 6670 driver had been modified to include a randomly selected quote on the separator pages. part of the audit was off-hours sweep of all the distributed printers ... looking for sensitive output that was left out/unattended. In one of the areas, the auditors found an output separator page with the following quote: [Business Maxims:] Signs, real and imagined, which belong on the walls of the nation's offices: 1) Never Try to Teach a Pig to Sing; It Wastes Your Time and It Annoys the Pig. 2) Sometimes the Crowd IS Right. 3) Auditors Are the People Who Go in After the War Is Lost and Bayonet the Wounded. 4) To Err Is Human -- To Forgive Is Not Company Policy. ... snip ... the next day, the auditors tried to escalate an issue that we were purposefully ridiculing them. In the wake of Enron, congress passed sarbanes-oxley that significantly increased audit requirements and penalties. A few years ago I was at a financial conference in europe of european corporate CEOs and exchange presidents ... major theme was that the (significant) SOX audit requirements and costs were leaking out into the rest of the world. There was semi-humorous reference to the country hosting the conference on sunday cnn gps program http://globalpublicsquare.blogs.cnn.com/2011/04/24/rent-the-country-of-liechtenstein-for-70k-a-night/ My position was that the increased audit requirements wouldn't make any significant dent in fraud (was more likely just a full-employment favor to the audit industry by congress) and possibly only significant part of SOX was section on informants. It turns out that apparently GAO also thot something similar and was doing reports of review of public company financial filings showing uptick in fraudulent filings after SOX (problem with both the audits and SEC enforcement). In congressional testimony by the person that had tried for a decade to get SEC to do something about Madoff, there was mention that tips turn up 13 times more fraud than audits and SEC didn't have a tip hotline, but had a 1-800 line for companies to complain about audits. -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: Dyadic vs AP: Was "CPU utilization/forecasting"
In <005a01cbff6c$b63dded0$22b99c70$@hawkins1...@sbcglobal.net>, on 04/20/2011 at 08:07 AM, Ron Hawkins said: >I remember spending some time playing with CPU affinity trying to >keep the CPU bound jobs away from the AP re: http://www.garlic.com/~lynn/2011f.html#49 Dyadic vs AP: Was "CPU utilization/forecasting" http://www.garlic.com/~lynn/2011f.html#50 Dyadic vs AP: Was "CPU utilization/forecasting" 360&370 had two-processor multiprocessor shared memory and although had dedicated channels ... tended to try and simulate shared channels by trying to configure the same channel numbers on the two processors so they connected to same controllers (at same addresses, for controllers that supported multiple channel attachments) ... allowing I/O to be done to the same controller/device by both processors. 370-APs only had one of the processors with channels ... the other processor was purely for dedicated execution. I/O requests that originated on the attahced processor (w/o channels ... or in multiprocessor for device only connected to channel on the other processor) ... resulted in internal kernel operation that handed off the i/o request to processor with the appropriately connected channel. one of the issues in cache machines ... was that high interrupt rates tended to have very deterious effect on cache-hit ratios (translates to effective MIP rate) ... where cache entries for the running application got replaced with cache entries for interrupt & device i/o handling ... and then possibly replaced again when switching back to the running application. A gimick I hased in the early/mid 70s for cache machine ... was when observed I/O interrupt rates exceeding threshold ... started running disabled for I/O interrupts ... but with periodic timer interrupt. At the timer interrupt, all pending interrupts would be "drained" under software control (using SSM to enable for i/o interrupts). The increased delay in taking the i/o interrupt was more than offset by both increased cache hit ratio (aka MIP rate) of the application running w/o interrupts, and then increased cache hit ratio (aka MIP rate) of effectively batch processing multiple I/O interrupts. For AP support, I also had a gimick that tended to keep the CPU intensive operations on the processor w/o channels (sort of natural CPU affinity). two processor 370 cache machine operation slowed down the processor machine cycle by 10% (for multiprocessor operation to take into account cross-cache communication) ... resulted in two-processor having base hardware of 1.8 times single processor ... multiprocessor software overhead then tended to result in multiprocssor having 1.4-1.5 times that of uniprocessor. For HONE 370APs, sometimes I could get 2-processor throughput more than twice single processor thruput. HONE was heavily compute intensive APL applications ... although some would periodically do lots of I/O. The natural processor/cache affinity (improved MIP rate) increased thruput (along with having extremely short multiprocessor support pathlengths) ... keeping the compute intensive (non I/O) application execution on the AP processor w/o channels. misc. past posts mentioning (virtual machine based) HONE (US HONE & HONE clones around the world provided world-wide sales & marketing support) http://www.garlic.com/~lynn/subtopic.html#hone This got messed up in the early 3081 dyadic time-frame. Since ACP/TPF didn't have multiprocessor support (and it hadn't yet been decided to do 3083) ... VM was "enhanced" to try and improve ACP/TFP 3081 virtual machine thruput. For a lot of VM pathlength that used to be serialized with virtual machine execution ... there was an attempt to make it asynchronous ... running on the 2nd, presumably idle processor ... with lots of request queuing and processor "shoulder taping" (the increase in overhead theoritically offset by the reduction in ACP/TPF elapsed time). However, for customers that had been running fully loaded (non-ACP/TPF) multiprocessor operation ... the transition to this new release represented significant degradation (the increased request queuing and shoulder taping taking 10-15% of both processors). Then there was a number of onsite visits at various large customers ... attempting to perform other kinds of tuning operations to mask the enormously increased multiprocessor overhead in the new release (all the shoulder taping also messed up the natural affinity characteristics ... motivating a large increase in explicit specified processor affinity). old email mentioning large gov. TLA ... trying to provide a variety of performance improvements to offset the multiprocessor overhead increase: http://www.garlic.com/~lynn/2001f.html#email830402 -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM
Re: Dyadic vs AP: Was "CPU utilization/forecasting"
l...@garlic.com (Anne & Lynn Wheeler) writes: > DYADIC was term introduced with 3081 ... where it wasn't possible to > split the configuration and run as two separate independent processors > (wanted to draw distinction between past 360/370 multiprocessor that > could be split and run independently and the 3081 which couldn't be > split). 3081 had both processors being able to address all channels and > also introducted 31-bit virtual addressing. re: http://www.garlic.com/~lynn/2011f.html#41 CPU utilization/forcasting http://www.garlic.com/~lynn/2011f.html#49 Dyadic vs AP: Was "CPU utilization/forecasting" during the FS period ... there was lots of internal politics going on and 370 product efforts were shutdown (as being possibly competitive). When FS died, there was all sort of mad rush to get things back into the 370 product pipelines (the distraction of FS is claimed to have also allowed clone processors to gain market foothold). ... this discusses some of the FS effort, the internal politics and the dark shadow that the FS failure cast over the corporation for decades" http://www.cs.clemson.edu/~mark/fs.html part of the mad rush was to get out q&d 303x. The integrated channel microcode from the 158 was split off into 303x "channel director" (158 engine with only integrated channel microcode and no 370 microcode). A 3031 was a 158 engine (& new panels) with just the 370 microcode (and no integrated channel microcode) and a 2nd 158 engine (channel director) with just the integrated channel microcode. A 3032 was a 168-3 with new panels and 303x channel director(s) aka 158 engine. A 3033 started out being 168-3 logic remapped to 20% faster chips and 303x channel director(s) ... before the 3033 shipped there was some redoing logic (the chips were 20% faster but also had ten times as much circuits per chip ... initially went unused) ... which got 3033 up to about 50% faster than 168-3. In parallel with 303x ... there was work on "811" architecture (supposedly named for nov78 date on lots of the documents) and the 3081 (a FS machine with just 370 emulation microcode). Some of this is discussed in this internal memo reference from the period: http://www.jfsowa.com/computer/memo125.htm A number of 3033up was starting to feel significantly memory/storage constrained being limited to maximum of 16mbyte real storage. It was much worse for 3033mp since they were also limited to same 16mbyte real storage constriant. A hack was done for 3033 to allow more real storage ... even tho instruction addressing was limited to 24bit/16mbyte addressing. The 370 page table entry had two unused bits ... and the 3033 hack was to re-assign the two unused bits to prepend them to the page number, allowing specifying up to 2**14 4kbyte pages (aka 26bit/64mbyte). Real & virtual instruction addressing was still limited to 16mbytes ... but a page table entry could translate that was up to 64mbytes. I/O then was done with IDALs ... which already had 31bit field. MVS was (also) having severe problems at larger 3033 installations. Transition from OS/VS2 svs to OS/VS2 mvs ... involved mapping 8mbyte MVS kernel image into every 16mbyte application virtual address space. In order to support subsystems that were now (also) in separate virtual address working with application address space ... there was "common segment" in every virtual address space, that started out as 1mbyte (applications being able to place parameters in CSA and use pointer-passing API in subsystem call). For large 3033 MVS instalaltions, CSAs were hitting 4-5mbytes and threatening to grow to 5-6mbytes (leaving only 2mbytes for application). An internal shop that was a large multiple machine MVS operation had 7mbyte fortran chip design application. The MVS operation was carefully configured to keep CSA to 1mbyte ... and constant ongoing activity keeping the chip design Fortran application from exceeding 7mbyte. They were being faced with having to convert all their machines to vm/cms ... since CMS could allow the application to have nearly all of the 16mbyte virtual address space. Early 3081Ds were shipped w/o the "811" extensions (vanilla 370 w/o 370-xa) and were supposedly slightly faster than 3033 ... however, there was a number of benchmarks that had 3081Ds 20% slower than 3033. 3081K came out with double the processor cache size ... supposedly 50% faster than 3033 ... but some benchmarks coming in only 5% faster than 3033. The internal memo (memntioned above) goes into the enormous amount circuits-hardware in 3081 compared to its performance (especially when stacked up against clone processors). tieing two 3081s into a 4-way 3084 really drove up the multiprocessor cache interference (invalidate signals coming from three other caches rather than one other cache). Both VM/HPO and MVS had kernel "cache sensitivity" work that involved carefully a
Re: Dyadic vs AP: Was "CPU utilization/forecasting"
martin_pac...@uk.ibm.com (Martin Packer) writes: > Ron, care to remind us of the modelling difference? It's been a while. :-) 360 & 370 dual-processors shared memory but each processors had its own dedicated channels ... and the configuration could be split and run as two separate processors. 370AP ... was a two processor configuration where only one of the processors had channels ... the second processor purely did compute bound work. it was less expensive and could be applicable to more compute intensive work. it was also applicable in large loosely-coupled environment when running out of controler interfaces for all the channels ... aka with four channel dasd controller with string-switch (for each disk connected to two controllers) ... giving 8 channel paths to each disk ... it would be possible to have eight two-processor complexes (for 16 processors total). DYADIC was term introduced with 3081 ... where it wasn't possible to split the configuration and run as two separate independent processors (wanted to draw distinction between past 360/370 multiprocessor that could be split and run independently and the 3081 which couldn't be split). 3081 had both processors being able to address all channels and also introducted 31-bit virtual addressing. trivia ... 360/67 had 32-bit virtual addressing, all processors could address all channels *AND* configuration could be split into independent running single processors. 360/67 was desgined for four-processor configuration, but I know of only a couple three-processor configuration that were actually built (and no four processor configurations) ... all the rest multiprocessor configurations were simply two-processors. other 3081 trivia ... 370 (& 3081) dual-processor slowed machine cycle down by ten percent to help with multiprocessor processor cache interaction ... so a two-processor machine started out at only 1.8 times a single processor machine. Multiprocessor software and actual multiprocessor cache interactions tended to add additional overhead so that dual-processor tended to have 1.4-1.5 times the throughput of single processor. 3081 originally never intended to have single processor version ... but largely because ACP/TPF didn't have multi-processor support, there was eventually a 3083 introduced. The easiest would have been to remove 2nd processor from the 3081 box ... however, processor0 was at the top of the box and the 2nd processor1 was in the middle of the box ... which would have left the box dangerously top heavy. eventually 3083 was introduced with single processor ... it was possible to turn-off the ten percent machine cycle slowdown (done for multiprocessor cache interaction) ... and eventually there was a special microcode load tuned for the ACP/TPF workloads that tended to be more I/O intensive. in the late 70s, the consolidated internal online US HONE operation (US HONE and the various HONE clones providied online world-wide sales & marketing support) was the largest single-system operation in the world. It was large loosely-coupled operation with "AP" multiprocessors ... most of the sales&marketing applications were implemented in APL and the workload was extremely compute intensive. I provided them with their initial multiprocessor support ... highly optimized kernel multiprocessor pathlengths and games played to improve cache hit locality ... could get slightly better than twice single processor (i.e. cache games offset the machine running at only 1.8times single processor and the optimized multiprocessor pathlengths). misc. past posts mentioning multiprocessor support (&/or compare&swap instruction) http://www.garlic.com/~lynn/subtopic.html#smp as mentioined in previous post http://www.garlic.com/~lynn/2011f.html#41 CPU utilization/forecasting the science center had done a lot of the early work in performance monitoring, reporting, simulation, modeling, workload&configuration profiling ... that evolves into capacity planning. misc. past posts mentioning science center http://www.garlic.com/~lynn/subtopic.html#545tech One of the APL models was packaged in the mid-70s as the "performance predictor" on HONE ... so that sales&marketing could take customer workload&configuration specification and ask "what-if" questions about workload &/or configuration changes. another version of the "model" was modified and used to decide (online) workload balancing across the loosely-coupled configuration (which processor complex would new logon be directed to, part of single-system operation). misc. past posts mentioning HONE http://www.garlic.com/~lynn/subtopic.html#hone -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: CPU utilization/forecasting
d...@lists.duda.com (David Andrews) writes: > Once upon a time I found it useful to condense a month's worth of RMF > data into a single graph showing the average CPU utilization over the > course of a day, plus-or-minus one standard deviation. That drop-bar > chart made it easy to visualize two-thirds of our daily workload at a > glance. in the early days of commercial virtual machine online service bureaus (sort of the cloud computing of the 60s & 70s) ... there were reports showing the peaks & troughs of avg. daily online use ... and being able to extend use over the whole country ... allowing the peaks from the different timezones to offset the troughs in other timezones. the science center had started accumulating all its (virtual machine) system activity from the 60s ... and established it as standard process for normal operation. By the mid-70s, the science center not only several years of its own data ... but was also acquiring similar data from large number of internal datacenters. This was used for a lot of modeling and simulation work, along with workload & configuration profiling ... which eventually evolves into capacity planning. one of the science center's models (implemented in APL) ... was made available (starting in the mid-70s) on the (internal online virtual machine) HONE systems (providing world-wide sales & marketing support) as the "Performance Predictor". Sales people could collect customer workload & configuration profile and ask "what-if" questions (of the "Performance Predictor") about changes to workloads and/or configuration. misc. past posts mentioning science center http://www.garlic.com/~lynn/subtopic.html#545tech -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: TCP/IP Available on MVS When?
l...@garlic.com (Anne & Lynn Wheeler) writes: > part of the issue was that the base support shipped with a box that was > basically a channel-attached bridge (similar but different to 3174 boxes > that supported LANs) ... so the host stuff had to do all the ARP/MAC/LAN > layer gorp ... rfc1044 support was channel attached tcpip-router ... so > a whole protocol layer was eliminated from host processing. > > well before the tcp/ip support in vtam ... there was considerable > misinformation regarding sna/vtam flying about ... including being > useable for NSFNET backbone (operational precusor to the modern > internet). re: http://www.garlic.com/~lynn/2011f.html#29 TCP/IP Available on MVS When? http://www.garlic.com/~lynn/2011f.html#30 TCP/IP Available on MVS When? additional trivia drift ... this is html version of internal IOS3270 "green card" (material from GX20-1850-3 and other sources) http://www.garlic.com/~lynn/gcard.html IOS3270 was cms application used for many applications ... including all the service panels in the (4361/cms) 3090 "service processor" ... old email reference http://www.garlic.com/~lynn/2010e.html#email861031 above is with respect to including a failure analysis/debug tool (I had written) as part of 3092. there had been a "blue card" for the 360/67 ... that included details of 67 features (like virtual memory support, multiprocessor control register detail) ... it also included sense data for several devices. I had provided the GCARD author with the sense data information. I had also included the sense data for the channel-attached tcp/ip router. I still have a "blue card" in a box someplace ... obtained at the science center from a fellow member (his name is "stamped" on the card). GML had been invented at the science center in 1969 ... GML actually is the first letter of the last names of the inventors (one of which is "stamped" on my blue gard). A decade later, in the late 70s, GML becomes a ISO standard as SGML. Another decade & SGML morphs into HTML: http://infomesh.net/html/history/early and the first webserver outside CERN, is on the SLAC VM/CMS system: http://www.slac.stanford.edu/history/earlyweb/history.shtml part of the significant sna/vtam misinformation campaign in the late 80s was to get the internal network converted over to sna/vtam. The campaign to convert the internal network backbone to sna/vtam was so thick that the backbone meetings were being restricted to management only (and technical people were being excluded) ... recently posted old email: http://www.garlic.com/~lynn/2011.html#email870306 in this post (linkedin Greater IBM discussion) http://www.garlic.com/~lynn/2011.html#4 Is Email dead? What do you think? In my HSDT effort I was doing multiple high-speed links and needed sustained aggregate thruput in excess of channel speeds (load spread across multiple mainframe channels). http://www.garlic.com/~lynn/subnetwork.html#hsdt Internal network VNET/RSCS used vm spool file system for intermediate storage. The API was synchronous and on heavily loaded system could limit thruput to 4-6 4kbyte blocks per second. I needed at least 100 times that thruput and had done a new API and (vm spool file) infrastructure to support sustained aggregate link thruput equivalent to multiple channels. The internal network had been larger than arpanet/internet from just about the beginning until late '85 or early '86. http://www.garlic.com/~lynn/subnetwork.html#internalnet and similar technology was used for BITNET/EARN (where this mailing list originated). http://www.garlic.com/~lynn/subnetwork.html#bitnet Rather than converting the internal network links to SNA/VTAM, it would have been sigificantly better, cost/effective, and efficient to have converted the internal network links to tcp/ip. -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: TCP/IP Available on MVS When?
l...@garlic.com (Anne & Lynn Wheeler) writes: > the company product was done on VM and implemented in vs/pascal > (5798-FAL). it had a number of thruput issues ... but I did the RFC1044 > enhancements and in some testing at Cray research ... between a 4341 and > cray ... got channel media sustained thruput using only modest amount of > 4341 cpu (about 500 times improvement in instructions executed per byte > moved). > misc. past posts mentioning rfc 1044 > http://www.garlic.com/~lynn/subnetwork.html#1044 re: http://www.garlic.com/~lynn/2011f.html#29 TCP/IP Available on MVS When? part of the issue was that the base support shipped with a box that was basically a channel-attached bridge (similar but different to 3174 boxes that supported LANs) ... so the host stuff had to do all the ARP/MAC/LAN layer gorp ... rfc1044 support was channel attached tcpip-router ... so a whole protocol layer was eliminated from host processing. well before the tcp/ip support in vtam ... there was considerable misinformation regarding sna/vtam flying about ... including being useable for NSFNET backbone (operational precusor to the modern internet). recent references to SNA/VTAM misinformation from the period: http://www.garlic.com/~lynn/2011.html#4 Is email dead? What do you think? http://www.garlic.com/~lynn/2011b.html#65 If IBM Hadn't Bet the Company http://www.garlic.com/~lynn/2011c.html#12 If IBM Hadn't Bet the Company http://www.garlic.com/~lynn/2011d.html#4 Is email dead? What do you think? http://www.garlic.com/~lynn/2011e.html#25 Multiple Virtual Memory http://www.garlic.com/~lynn/2011e.html#32 SNA/VTAM Misinformation http://www.garlic.com/~lynn/2011e.html#34 SNA/VTAM Misinformation http://www.garlic.com/~lynn/2011e.html#43 junking CKD; was "Social Security Confronts IT Obsolescence" http://www.garlic.com/~lynn/2011e.html#57 SNA/VTAM Misinformation http://www.garlic.com/~lynn/2011e.html#77 Internet pioneer Paul Baran http://www.garlic.com/~lynn/2011e.html#83 History of APL -- Software Preservation Group misc. old email regarding working with NSF on various activities leading up to NSFNET backbone: http://www.garlic.com/~lynn/lhwemail.html#nsfnet This has postings regarding various announcements http://vm.marist.edu/~vmshare/browse?fn=IBMNEW89&ft=MEMO from above posted 9/21/84: VM Interface Program for TCP/IP (5798-DRG): Provides VM user the capability of participating in a network with TCP/IP transmission protocol. Includes ability to do file transfers, send mail, and log on remotely to VM hosts. (Comment: It's not clear whether this equals VM access to non-VM hosts such as are found on ARPANET. I believe this is the same product as WISCNET, already available to academic shops.) ... snip ... and from above posted 4/22/87: IBM also announced the new TCP/IP facility (5798-FAL) on 4/21/87. This package replaces the old program (5798-DRG) and includes some programs for PCs. The announcement is 287-165. To quote: "... IBM TCP/IP for VM provides the VM/SP, VM/SP HPO, or VM/XA SF user with the capability of participating in a multi-vendor Internet network using the TCP/IP protocol set. This protocol set is an implementation of several of the standard protocols defined for the Defense Advanced Research Projects Agency. The use of these protocols allows a VM user to interface with other systems that have implemented the TCP/IP protocols. This connectivity includes the ability to transfer files, send mail, and log on to a remote host in a network of different systems. The IBM TCP/IP for VM program uses a System/370 channel attached to a variety of controllers or devices for connection to the selected network. The network protocols supported are IBM Token-Ring, Ethernet(1) LAN, ProNET(2) and DDN X.25. IBM TCP/IP for VM offers IBM TCP/IP for the PC as an optional feature, allowing the user of an IBM personal computer on an IBM Token-Ring or Ethernet LAN to communicate with the VM system using the TCP/IP protocols." Announced devices supported are the IBM Series/1, 7170 DACU, and 9370 LAN adapters (Token Ring or Lan) ... snip ... -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: TCP/IP Available on MVS When?
steve_con...@ao.uscourts.gov (Steve Conway) writes: > OK, let's invoke Jaffe's Law (Any ibm-main discussion will eventually > become a history lesson) immediately. > > In this case, I need a history lesson, preferably with citable references. > > When (year and OS release, if available) did TCP/IP become available for > VM? For MVS? > > No forum is more perfectly suited for my question. :-) the company product was done on VM and implemented in vs/pascal (5798-FAL). it had a number of thruput issues ... but I did the RFC1044 enhancements and in some testing at Cray research ... between a 4341 and cray ... got channel media sustained thruput using only modest amount of 4341 cpu (about 500 times improvement in instructions executed per byte moved). misc. past posts mentioning rfc 1044 http://www.garlic.com/~lynn/subnetwork.html#1044 vmshare reference to 5798-fal: http://vm.marist.edu/~vmshare/browse?fn=TCPIP&ft=PROB the base implementation was later made available on MVS by moving over the VM code and writting a simulation for some of the VM functions. later there was a contract to implement tcp/ip support in VTAM. the folklore is that when the implementation was first demo'ed ... the company said that it was only paying for a "correct" implementation ... and everybody knows that a "correct" tcp/ip implementation is significantly slower than LU6.2 (not significantly faster). The contract was handled by "local" ibm office in Palo Alto Sq office bldg. now predating products ... there was various univ. implementations ... reference to tcp/ip at UCLA MVS in late 70s: http://en.wikipedia.org/wiki/Bob_Braden predates the great switchover from host/imp protocol to tcp/ip protocol on 1jan83. -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: Fear the Internet, was Cool Things You Can Do in z/OS
scott_j_f...@yahoo.com (Scott Ford) writes: > Well 1987 wow before the real firewalls. Security was on the inbound/outbound > dial devices. Also worked VM, cut my teeth on VM/SP1 > , loved VM, still do, I can how a exec would cause major pain in a VM system, > no > doubt. z/OS would be a bit tougher I would think, plus a pre-req would be > enough > knowledge to get in and be able to execute, plus passwords and ids...A lot of > research and work ...just to hack a MF re: http://www.garlic.com/~lynn/2011f.html#23 Fear the Internet, was Cool Things You Can Do in z/OS http://www.garlic.com/~lynn/2011f.html#24 Fear the Internet, was Cool Things You Can Do in z/OS big difference between internal network and the internet in the 80s ... was that all internal network links (that left corporate premise) had to be encrypted. could be a big pain ... especially when links crossed certain national boundaries. in the mid-80s, it was claimed that the internal network had over half of all link encryptors in the world. company also did custem encrypting PC (2400 baud) modems for corporate home terminal program. there is folklore that one high-ranking (EE graduate) executive was setting up his own installation at home. supposedly at one point he stuck his tongue in rj11 jack (to see if their was any juice ... old EE trick) ... just as the phone rang. After that there was a corporate edict that all modems made by the company had to have the jack contacts recessed sufficiently so babies (and executives) couldn't touch them with their tongue. http://en.wikipedia.org/wiki/RJ11 i had an HSDT (high-speed data transport) project and was dealing with T1 links & higher speed. T1 link encryptors were really expensive ... but you could get them ... but I to start work on my own to go significantly faster. misc. past posts mentioning HSDT http://www.garlic.com/~lynn/subnetwork.html#hsdt big difference in worms/viruses (and various other exploits) and social engineering ... is that social engineering requires active participation by the victim (current flavors frequently advertise download & execute things, frequently of very dubious nature; games, videos, etc). allowing users to execute arbitrary (unvetted) programs was identified as vulnerability at least back in the 70s (if not the 60s). somewhat more recent thread (with some of my comments copied from another venue) How is SSL hopelessly broken? Let us count the ways; Blunders expose huge cracks in net's trust foundation http://www.theregister.co.uk/2011/04/11/state_of_ssl_analysis/ with regard to above we had been called in to consult with small client/server startup that wanted to do payment transactions on their server, they had also invented this technology called SSL they wanted to us (the result is now frequently called "electronic commerce"). By the time we were finished with the deployments ... most of the (current) issues were very evident. very early in the process I had coined the term "comfort certificate" ... since the digital certificate actually created more problems than it solved ... in fact, in many cases, it was totally redundant and superfluous ... and existed somewhat as magic "pixie dust" ... lots of old posts mentioning SSL digital certificates: http://www.garlic.com/~lynn/subpubkey.html#sslcert There was two parts of SSL deployment for "electronic commerce" ... between the browser and webserver and between the webserver and the "payment gateway" ... I had absolute authority over interface deployment involving "payment gateway" ... but had only advisory over browser/webserver. There were a number of fundamental assumptions related to SSL for browser/webserver secure deployment ... that were almost immediately violated by merchant webservers (in large part because of the high overhead of SSL cut their throughput by 85-90%). I had mandated mutual authentication for webserver/gateway (implementation didn't exist originally) and by the time deployment was done the use of SSL digital certificates was purely a side-effect of the crypto library being used. the primary use of SSL in the world today is electronic commerce for hiding payment transaction information. The underlying problem is the transaction information is dual-use both authentication and needed by dozens of business processes in millions of of places around the world. In the X9A10 financial working group we (later) directly addressed the dual-use problem with the x9.59 financial standard (directly addressing the problem, x9.59 is significantly lighter weight than SSL as well as KISS). This eliminated the need to hide the transaction details ... also eliminates the threat from majority of data breaches (doesn't eliminate data breaches, just eliminates crooks being able to use the information for fraudulent purposes). Problem (as always) is there is significant vested interests in the current status quo. -- virtualization experience starting Jan1968, online at home since Mar1970
Re: Fear the Internet, was Cool Things You Can Do in z/OS
scott_j_f...@yahoo.com (Scott Ford) writes: > > ??? whats it XMASCARD recent post http://www.garlic.com/~lynn/2011b.html#9 mentions: there was xmas exec on bitnet in nov87 ... vmshare archive http://vm.marist.edu/~vmshare/browse?fn=CHRISTMA&ft=PROB and was almost exactly a year before (internet) morris worm (nov88) http://en.wikipedia.org/wiki/Morris_worm xmas exec was social engineering ... similar go some current exploits which advertise something that victim has to download and then (manually) explicitly execute (requires victim's cooperation). some additional http://www.garlic.com/~lynn/2011b.html#10 misc. past posts mentioning bitnet (&/or earn) http://www.garlic.com/~lynn/subnetwork.html#bitnet which used technology similar to the corporate internal network (larger than arpanet/internet from just about the beginning until late '85 or early '86): http://www.garlic.com/~lynn/subnetwork.html#internalnet ... and http://www.garlic.com/~lynn/2011f.html#23 "fix" previous reference (missing trailing "l"): http://www.nsa.gov/research/selinux/list-archive/0409/8362.shtml in '89 there was several messages that were sent out that major internal corporate (MVS-based) administrative systems had fallen victim to a virus ... however after several iterations it was eventually announced that the systems were suffering from some bug. this selection of some internet related items/posts starts out with reference to corporate installed email gateway in fall of '82 http://www.garlic.com/~lynn/internet.htm -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: Fear the Internet, was Cool Things You Can Do in z/OS
mike.a.sch...@gmail.com (Mike Schwab) writes: > Writing the SE Linux was done with a National Security Agency (No Such > Agency) (NSA) research grant. > http://www.nsa.gov/research/selinux/ also from long ago and far away: http://www.nsa.gov/research/selinux/list-archive/0409/8362.shtm -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: New job for mainframes: Cloud platform
shmuel+ibm-m...@patriot.net (Shmuel Metz , Seymour J.) writes: > Access registers were ESA; they were announced for the 3090. Was the > 3081 a testbed for them, or was that a typo? re: http://www.garlic.com/~lynn/2011f.html#12 New job for mainframes: Cloud platform http://www.garlic.com/~lynn/2011f.html#17 New job for mainframes: Cloud platform sorry ... access registers were in the "811" architecture documents (supposedly named for the nov78 date on most of the documents) ... "811" pieces then leaked out in various machine levels. some of the (3033 &) 3081 discussed in detail here http://www.jfsowa.com/computer/memo125.htm ... "811", 3033 and 3081 were hurry-up patch up efforts recoverying from the FS disaster ... some more discussion in this (linkedin) "Greater IBM" (current & former IBMers) http://www.garlic.com/~lynn/2011f.html#2 Car models and corporate culture: It's all lies http://www.garlic.com/~lynn/2011f.html#13 Car models and corporate culture: It's all lies it wasn't until 3090 ... that you start to see a "real" new machine (including vm/cms 4361&3370s being the service processor in all 3090s ... even 3090s that nominally had operating system w/o 3370FBA support). -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: New job for mainframes: Cloud platform
gra...@ase.com.au (Graeme Gibson) writes: > Well, let's not skew the kiddie's brains too much.. re: http://www.garlic.com/~lynn/2011f.html#12 New job for mainframes: Cloud platform yes, well ... I thot it was also interesting that 2702 (IBM line scanners) managed to (also) reverse bits within bytes (before x86 even appeared on the scene). other trivia was HP had major hand in Itanium (designed to be dual-mode ... both big-endian & little-endian) ... which at one time was going to be the "mainframe killer" ... since then lots of Itanium business critical features have been migrated to XEON chips (and various recent news items projecting death of Itanium). major person behind wide-word & Itanium had earlier been responsible for 3033 dual-address space mode ... retrofitted a little of 370-xa access registers to 3033 to try and slow the exploding common segment problem (with 24-bit, 16mbyte virtual address space ... and MVS kernel image taking half of each virtual address space ... large installations were approaching situation where CSA was going to be 6mbytes ... reducing space for applications to 2mbytes). itanium stuff http://www.hpl.hp.com/news/2001/apr-jun/worley.html other pieces from wayback machine: http://web.archive.org/web/20010722130800/www.hpl.hp.com/news/2001/apr-jun/2worley.html http://web.archive.org/web/2816002838/http://www.hpl.hp.com/features/bill_worley_interview.html internal IBM had some critical chip-design tools implemented in Fortran running on large number of carefully crafted MVS systems ... and were having increasingly difficult time to keep the application under 7mbytes (MVS kernel image at 8mbytes and minimum CSA size was 1mbyte, leaving maximum of 7mbytes for applications) ... they were being faced with having to convert the whole operation to vm/cms ... since that would allow them to have nearly whole 16mbytes for application. -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: Identifying Latest zOS Fixes
mike.a.sch...@gmail.com (Mike Schwab) writes: > Most of your Micro$oft and Linux errors are due to the C language > defining an end of string as x'00', and the programmer forgetting to > check the lenght of the input against the buffer. The the hacker > sends a malformed string to that function and overlays the program > code and takes control. buffer length related problems dominated through the 90s ... misc past posts http://www.garlic.com/~lynn/subintegrity.html#buffer much of desktop evolved in purely stand-alone enviornment ... with some early (3270) terminal emulation. then was added, private, business, closed, "safe", network support ... with lots of applications & files that included automated "scripted" enhancements. At the 1996 MDC (held at Mascone) there were huge number of banners about moving to internet (simple remapping of the networking conventions w/o the corresponding countermeasures involved moving from "safe" environment to extremely "hostile" environment; periodic analogy with going out airlock into open space w/o space suit). However, the constant subtheme (at '96 MDC) was "protecting your investment" ... referring to all the scripting capability. Starting early part of this century, such exploits began to clipse the buffer length problems ... along with the heavy weight security convention of analyze/filtering incoming files against an enormously bloated library of possible exploit "signatures" old post doing word frequency analysis of CVE "bug" reports ... and suggesting to mitre that they require a little more formal structure in the reports (at the time, I got pushback that they were lucky to get any reasonable verbage): http://www.garlic.com/~lynn/2004e.html#43 security taxonomy and CVE more recent reference to CVE ... which has since moved to NIST http://www.garlic.com/~lynn/2011d.html#8 Security flaws in software development note that the original mainframe tcp/ip protocol stack had been done in vs/pascal ... and suffered none of the buffer length exploits found in C-language implementations. there were other thruput and pathlength issues with that implementation ... but I did the RFC1044 enhancements for the implementation ... and in some testing at Cray Research ... got sustained channel throughput between Cray and 4341 ... using only modest amount of 4341 processor. misc. past posts mentining RFC1044 support http://www.garlic.com/~lynn/subnetwork.html#1044 -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: New job for mainframes: Cloud platform
timothy.sipp...@us.ibm.com (Timothy Sipples) writes: > I've known HP in its sales pitches to make a lot of fuss about > endianness as reason why it would be oh-so-difficult for an HP-UX > customer to move to Linux on X86, or for a Linux X86 customer to move > to (or add) Linux on System z, depending on their sales > situation. Then hundreds/thousands of HP customers moved without > endianness difficulty, and many more will follow. The IT community > figured out how to flip bit order a long time ago. Before System/360, > even. That's not to say endianness isn't a problem...for HP. If they > want to move HP-UX to a little endian CPU, they'll have a lot of > investment to do (as Sun did for Solaris X86). For non-OS > kernel/non-compiler programmers, which is the vast majority of us, > it's not a real-world problem. In fact, endianness is one of the least > interesting issues when porting from one CPU to another. re http://www.garlic.com/~lynn/2011f.html#7 New job for mainframes: Cloud platform http://www.garlic.com/~lynn/2011f.html#9 New job for mainframes: Cloud platform when I was undergaduate in the 60s, some people from the science center came out and installed (virtual machine) cp67 on the 360/67 (as alternative to tss/360). cp67 had "automatic" terminal identification for 1052 & 2741 ... playing games switching the line-scanners with the 2702 SAD command. The univ. had bunch of TTY/ascii terminals ... so I set out to add TTY/ascii support also doing automatic terminal identification. It almost worked ... being able to dynamically identify 1052, 274, & TTY for directly/fixed connect lines. I had wanted to have a single dial-up number for all termainls ... with "hunt-group" ... allowing any terminal to come in on any port. The problem was that the 2702 took a short-cut and hardwired the line-speed for each port. This somewhat prompted the univ. to do a clone controller effort ... to dynamically do both automatic termeinal & automatic speed determination (reverse engineer channel interface, build controller interface board and program minicomputer to emulate 2702). Two early "bugs" that stick in my mind ... 1) the 360/67 had high-speed location 80 timer ... and if the channel interface board held the memory bus for two consecutive timer-tics (a timer-tic to update location 80 was stalled because memory bus was held ... and the next timer-tic happened while the previous timer-tic was still pending), the processor would stop & redlight 2) initial data into memory was all garbage. turns out had overlooked bit memory order. minicomputer convention was leading (byte) bit off the line started off into high-order (byte) bit position ... while 2702 line-scanner convention was to place leading (byte) bit off the line in the lower order (byte) bit position. while the minicomputer then was placing data into memory in line-order bit positiion ... each byte had the bit order reversed compared to the 2702 convention (standard 360 ascii translate tables that I had borrowed from BTAM handled the 2702 bit-reversed bytes). ... later, four of us get written up for being responsible for some portion of the mainframe clone controller business. A few years ago, in large datacenter, I ran across a descendent of our original box, handling a major portion of the dial-up POS cardswipe terminals in the country (some claim that it still used the original channel interface board design). I had posted same cloud item in a number of linkedin mainframe group http://www.garlic.com/~lynn/2011f.html#6 New job for mainframes: Cloud platform http://www.garlic.com/~lynn/2011f.html#8 New job for mainframes: Cloud platform also http://lnkd.in/F6X_3Y also refers to internal (virtual machine) HONE system being the largest "cloud" operation in the 70s & 80s. In the mid-70s, the US HONE datacenters were consolidated in silicon valley ... where it created the largest single-system-image cluster operation. Then in the early 80s, because of earthquake concerns, it was replicated in Dallas ... with distributed, load-balancing and fall-over between Dallas & PaloAlto ... eventually growing to 28 3081s. misc. past posts mentioning HONE http://www.garlic.com/~lynn/subtopic.html#hone HONE also discussed in this linkedin Greater IBM (current & former IBM employee) group about APL software preservation (major portion of HONE applications supporting worldwide sales & marketing had been implemented in APL; numerous HONE-clones all around the world): http://www.garlic.com/~lynn/2011e.html#83 History of APL -- Software Preservation Group http://www.garlic.com/~lynn/2011f.html#3 History of APL -- Software Preservation Group http://www.garlic.com/~lynn/2011f.html#10 History of APL -- Software Preservation Group http://www.garlic.com/~lynn/2011f.html#11 History of APL -- Software Preservation Group another cloud related item: Facebook Opens Up Its Hardware Secrets; The social network breaks an unwritten rule by giving away plans to its new data cent
Re: New job for mainframes: Cloud platform
ibm-m...@tpg.com.au (Shane Ginnane) writes: > And how is any of this news ?. > (comment aimed at the wider community, not Lynn specifically) re: http://www.garlic.com/~lynn/2011f.html#7 previous was from several days ago ... more recent items from today: IBM Jumps Into Cloud, Customers Tip-toe Behind http://www.pcworld.com/businesscenter/article/224688/ibm_jumps_into_cloud_customers_tiptoe_behind.htm IBM Forecasts $7 Billion In Cloud Revenue http://www.informationweek.com/news/cloud-computing/platform/229401103 there is also some additional discussion in the linkedin mainframe group URL http://lnkd.in/F6X_3Y -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
New job for mainframes: Cloud platform
New job for mainframes: Cloud platform http://www.computerworld.com/s/article/9214913/New_job_for_mainframes_Cloud_platform from above: As companies take steps to develop private clouds, mainframes are looking more and more like good places to house consolidated and virtualized servers. Their biggest drawback? User provisioning is weak. ... snip ... also: http://lnkd.in/F6X_3Y -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: Cool Things You Can Do in z/OS
t...@harminc.net (Tony Harminc) writes: > The criteria are quite different. A public phone system that connects > 0.0001 percent of calls to the wrong place and drops a similar number > in mid call is perfectly acceptable. A phone system (even a single > local switch serving 10,000 lines) that is down for one minute a week > is completely unacceptable. re: http://www.garlic.com/~lynn/2011f.html#4 Cool Things You Can Do in z/OS there was an incident a few years back where the 1-800 mapping for major percentage of the POS (point-of-sale) card-swipe terminals in the US was down for 12 minutes during a mid-day period ... this was treated as a serious corporate incident between major transaction processor and major telco operation. five-nines availability is something like 5min (total) outage per year (includes both scheduled and unscheduled). -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: Cool Things You Can Do in z/OS
s...@pscsi.net (Sam Siegel) writes: > Please consider the RAS on the US domestic phone switching network. > It is a distributed system that (to my knowledge) does not use z/OS or > zSeries hardware. You also have service providers like Google, the > global DNS servers, etc. The list can be easily extended to > demonstrate extremely good RAS overall on a distributed system where > high RAS is deemed important. long ago & far away ... my wife had been con'ed into going to POK to be in charge of loosely-coupled architecture ... where she did "peer-coupled shared data" architecture ... which except for IMS hot-standby, saw very little update until sysplex & parallel sysplex. She didn't remain very long ... in part because of the slow uptake ... but also the periodic battles with the communication group trying to force her into using SNA for loosely-coupled operation. misc. past posts mentioning peer-coupled shared data architecture http://www.garlic.com/~lynn/submain.html#shareddata when we were doing HA/CMP product for the company ... I had coined the terms "disaster survivability" and "geographic survivability" (to differentiate from disaster/recovery). I had also been asked to write a section for the corporate continuous availability strategy document ... but it got pulled when both Rochester (as/400) and POK (mainframe) complained (that they couldn't meet the requirements). We also did some work with the 1-800 service (database service that maps 1-800 numbers to "real" exchange number ... required five-nines availability). misc. past posts mentioning ha/cmp http://www.garlic.com/~lynn/subtopic.html#hacmp later we had some dealings with one of the large financial transaction infrastructures ... and they attributed thier multiple year, 100% availability to * geographically separated, replicated IMS hot-standby operation * automated operator i.e. as hardware has became much more reliable ... unscheduled outages came to be dominated by environmental issues/outages and human mistakes -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: coax (3174) throughput
r.skoru...@bremultibank.com.pl (R.S.) writes: > Yes, however my curiosity is related only to coax port - coax port > "channel". In this scope any other bottleneck does not apply. Of > course in real word the weakest link of chain is the most important. > BTW: 3174 can be channel-attached, and I guess that ESCON is not a > bottleneck for coax, even 32 of them. re: http://www.garlic.com/~lynn/2011e.html#94 coax (3174) throughput I never measured 3174 ... the 3274 had the opposite problem ... not only did moving lot of electronics out of the head back to shared control unit ... enormously increase coax cable chatter and slow down thruput (i.e. both the amount of chatter on the coax as well as latency for all the back and forth to support really "dumbed down" 3278) ... but the slow electronics in the 3274 had significant hit on (bus&tag) channel busy (transfer rate 640kbytes on the channel side ... but really slow handsaking made raw transfer rate only small part of the channel busy ... analogous to all the really slow handshaking on the coax side enormously slowing down effective response time and transfer rate). I had done a project for the IMS group when STL was bursting at the seams and 300 were being put at remote site ... with datacenter support back to STL. They had tested "remote" 3278 support back to STL and found it truely horrible and totally unacceptable ... local channel attach 3278 were bad enough having hard time making subsecond response http://www.garlic.com/~lynn/2001m.html#19 3270 protocol but for "remote" 3278, it wasn't even "remotely" possile :-) The side effect of doing support for channel-extender ... allowing "channel" attached 3274s controllers to put at the remote location (and providing 3278 response at remote location, that was indistinquishable from local channel attach), the channel-extender boxes had significantly faster channel interface processing ... getting the 3274s off the real channels improved local processor thruput by 10-15%. When 3278s originally came out ... we complained loudly to the product group about 3278 interactive performance vis-a-vis 3277. Eventually the product group came back with the reply that 3278s weren't designed for interactive computing but for "data entry" (aka basically online "upgrade" for card punch machines). The controller channel busy overhead (independent of raw transfer rate) was to raise its head again with 3090 and 3880 disk controllers (3mbyte transfer rate). The 3880 channel busy overhead turned out to be so high, 3090 product realized that it had to add a whole bunch additional channels ... which resulted in having to add an extra TCM to 3090 manufacturing (there were jokes that the 3090 group was going to bill the 3880 product group for the cost of the increased 3090 manufacturing cost). This was sort of the leading edge of theme that mainframes with enormous number of channels being a good thing (when it was actually to compensate for the channel/controller interface design and slow controllers would drastically reduce channel effectiveness). a couple recent posts: http://www.garlic.com/~lynn/2011.html#37 CKD DASD http://www.garlic.com/~lynn/2011e.html#15 At least two decades back, some gurus predicted that mainframes would disappear in future and it still has not happened -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: coax (3174) throughput
r.skoru...@bremultibank.com.pl (R.S.) writes: > What is the throughput of coax connection? > I'm aware hat it's usually used for "hard" terminal connectivity, > i.e. 3278 to 3174 and speed is simply good enough. > However let's imagine PC with coax card connected to 3174 and IND$FILE > transfer. What throughput can be expected? comparison of 3277/3272 to 3278/3274 (3174 precursor). big dropoff in 3278 thruput was that a lot of the electronics in the 3277 head had been moved back into the (shared) controller (reducing 3278 terminal manufacturing costs) ... drastically increasing the chatter over the coax (and reducing thruput and response). This was also seen later in upload/download speeds using 3277 emulation cards versus 3278 emulation cards (because of difference in coax protocol/chatter): http://www.garlic.com/~lynn/2001m.html#19 3270 protocol 3277 emulation had three times the upload/download thruput of 3278 emulation http://www.garlic.com/~lynn/2009l.html#60 ISPF Counter reference to possibly 15kbytes/sec http://www.garlic.com/~lynn/2005r.html#17 Intel strikes back with a parallel x86 design above are direct channel attached controllers. for a little recent topic drift (not direct channel attach 327x controller) http://www.garlic.com/~lynn/2011e.html#88 Would mainframe technology be releveant in the age of cloud computing? -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: Mainframe Fresher
st...@trainersfriend.com (Steve Comstock) writes: > But I am curious as to why the mainframe doesn't just go > away: there must be one or more z/OS applications that the > Windows folks just can't beat. Can you describe what applications > are keeping the mainframe around? And why Windows folks can't > make it go away? lots of online/real-time stuff in the 70s & 80s was adding frontend that started an operation ... but left it to (existing, frequently cobol) legacy batch operation to complete (/settle) ... moved to "overnight batch window". in the 90s, the "overnight batch window" was becoming major bottleneck ... globalization both increasing workload ... as well as pressure to significantly decrease length of the "overnight batch window". in this period, some number of institutions spent billions on business process reengineering that would leverage massive parallelization and "killer micros" to implement "straight through processing" (running each operation straight through to completion & eliminating need for overnight batch window). however, it turned out that they used some technology that wasn't adequately vetted ... and going into deployment they found that it had overhead 100 times that of the cobol batch (and wouldn't scale) ... totally swamping anticipated (parallel) throughput improvements. the resulting failures left huge scars on the industry and stalled reengineering efforts for possibly decades. I was involved in taking a whole new generation of parallelization to some industry bodies a couple years ago ... and while it initially met very positive acceptance ... as it moved up individual institutions ... it met quite a bit of resistance ... apparently even nearly a decade later ... the scars from the failures were still fresh. -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: Mainframe passwords synced to active directory.
mellonb...@yahoo.com (Bill Johnson) writes: > We are trying to sync up (and expand) our mainframe passwords to match > what the user has in active directory. So far so good. The problem is > when the AD password is longer than 8 characters. Anyone shed some > light as to how this can be handled? active directory trivia ... based on kerberos http://technet.microsoft.com/en-us/library/bb742516.aspx original implementation for active directory was done under contract by one of the companies providing commercial kerberos products. over the years ... active directory drifted from kerberos base ... some discussion on interoperability http://www.centrify.com/blogs/tomkemp/integrating_mit_kerberos_with_active_directory.asp kerberos http://en.wikipedia.org/wiki/Kerberos_%28protocol%29 part pf MIT's project athena http://en.wikipedia.org/wiki/Project_Athena with joint funding by DEC and IBM to the tune of $25M each. started in the early day's of IBM's ACIS and getting much more active with universities. we use to drop by Project Athena periodically as part of corporate review of what was going on (was there for early discussions on how multiple relm interoperability would work). article about kerberos on mainframe (seamless interoperability with RACF) http://www.mainframezone.com/it-management/kerberos-on-z-os-teaching-an-old-dog-new-tricks/P2 much later at presentation for a SAML product multi-relm deployment (coalition forces) ... and happened to observe/mention that SAML messages & message flows look nearly the same as Kerberos (with the format of the message contents being XML) http://en.wikipedia.org/wiki/SAML_2.0 the speaker was somewhat defensive saying that there are only a limited number of ways to do multi-relm implementation. -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: Internet pioneer Paul Baran
l...@garlic.com (Anne & Lynn Wheeler) writes: > the majority of the internal nodes had always been VM ... but starting > in the late 70s there was an explosion in the number of vm/4341 nodes. re: http://www.garlic.com/~lynn/2011e.html#77 Internet pioneer Paul Baran There a huge number of JES/NJE issues. For some time the code carried "TUCC" identifier in assembler source from HASP days. For node definition, it took unused slots in the HASP 255 entry psuedo device table. Normal installation could have 60-100 psuedo devices ... leaving a maximum off 160-200 entries for defining network nodes. By the time the NJE software shipped to customers there were more nodes than could be defined in NJE (VNET had a totally different native implementation that had an enormously larger limitation related to number of network nodes). NJE software also would discard any traffic where it didn't have either the origin or destination node defined (even if it knew how to deliver the traffic, if it didn't have definition for the origin, it would still discard). sometime after the internal network passed 1000 nodes, NJE was enhanced to handle 999 nodes ... and after the internal network node passed 2000 nodes, NJE was enhanced to handle 1999 nodes. Another problem was that NJE jumbled networking and job control fields ... and incompatibilities between two different NJE releases could result in crashing MVS. As a result, a large library of VNET/RSCS drivers grew-up ... that would do canonical conversion of NJE header information ... with specific driver being started in VNET/RSCS being started that corresponded to the release level of JES/NJE on the other end of a link (as a countermeasure to keep MVS from crashing). A combination of these problems restricted JES systems to boundary nodes ... with VM handling core networking operation (and the majority of all nodes). There is the infamous scenario where VNET/RSCS NJE driver wasn't updated and started ... resulting in traffic from a MVS/JES system in San Jose resulting in MVS/JES system in Hursley crashing (and management blaming VNET/RSCS for +not keeping MVS from crashing). misc. past posts mentioning HASP, JES, &/or NJE networking http://www.garlic.com/~lynn/submain.html#hasp a footnote on the conversion to SNA/VTAM ... given the enormous resources that were pumped into the effort ... it would have been much more efficient to have converted RSCS/VNET to tcp/ip ... rather than SNA/VTAM. for the fun of it ... from IBM Jargon: notwork - n. VNET (q.v.), when failing to deliver. Heavily used in 1988, when VNET was converted from the old but trusty RSCS software to the new strategic solution. To be fair, this did result in a sleeker, faster VNET in the end, but at a considerable cost in material and in human terms. nyetwork, slugnet slugnet - n. VNET (q.v.) on a slow day. Some say on a fast day, and especially in 1988. notwork, nyetwork ... snip ... some bitnet history: http://en.wikipedia.org/wiki/BITNET http://www.livinginternet.com/u/ui_bitnet.htm above mentions BITNET II about the time of NSFNET backbone ... again it would have been much better if the internal network cutover had gone to tcp/ip than SNA/VTAM. old email regarding various aspects of NSFNET backbone http://www.garlic.com/~lynn/lhwemail.html#nsfnet and old email about getting EARN going (effectively BITNET in Europe): http://www.garlic.com/~lynn/2001h.html#email840320 in this post http://www.garlic.com/~lynn/2001h.html#65 -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: Internet pioneer Paul Baran
efinnel...@aol.com (Ed Finnell) writes: > Was it Walt Dougherty(sp) that used to give the networks update at SHARE > early eighties? Started with a two page binder and mid-eighties was about an > inch and half of Fanfold... re: http://www.garlic.com/~lynn/2011e.html#76 Internet pioneer Paul Baran this is old post that contains announcement in 1983 for the 1000th node on the internal network ... as well as a couple samples of other 1983 new node announcements http://www.garlic.com/~lynn/99.html#112 the majority of the internal nodes had always been VM ... but starting in the late 70s there was an explosion in the number of vm/4341 nodes. this post has samples of 1983 new node announcements ... as well as the list of all (world-wide) locations have new nodes added during 1983 http://www.garlic.com/~lynn/2006k.html#8 and followup post http://www.garlic.com/~lynn/2006k.html#43 in the 70s they used some layout software to print nodes and connections (when it was few hundred). printed on back of green-bar fanfold 1403/3211 ... boxes and connecting lines. Old post about (still) having one printed on 15apr1977 at HONE1 (in box some place) http://www.garlic.com/~lynn/2002j.html#4 this ibm-main mailing list originated on bitnet (& earn) which was corporate sponsored network of higher educational institutions ... using similar technology to that used in the internal network http://www.garlic.com/~lynn/subnetwork.html#bitnet one of the issues was that the (customer) vnet/rscs drivers quickly become restricted to just the NJI family of drivers ... which were much less efficient than the vnet/rscs native drivers ... that continued to be used internally ... at least up until the internal network switch-over to SNA in the late 80s. There was all sorts of resistance to converting the internal network (to sna/vtam) and so the communication group had large campaign to drive it through ... including telling top corporate executives things like PROFS was a VTAM application (as part of justification). a number of recent posts mentioning san/vtam misinformation activity in the late 80s: http://www.garlic.com/~lynn/2011.html#4 Is email dead? What do you think? http://www.garlic.com/~lynn/2011b.html#65 If IBM Hadn't Bet the Company http://www.garlic.com/~lynn/2011c.html#12 If IBM Hadn't Bet the Company http://www.garlic.com/~lynn/2011d.html#4 Is email dead? What do you think? http://www.garlic.com/~lynn/2011e.html#25 Multiple Virtual Memory http://www.garlic.com/~lynn/2011e.html#32 SNA/VTAM Misinformation http://www.garlic.com/~lynn/2011e.html#34 SNA/VTAM Misinformation http://www.garlic.com/~lynn/2011e.html#43 junking CKD; was "Social Security Confronts IT Obsolescence" http://www.garlic.com/~lynn/2011e.html#57 SNA/VTAM Misinformation -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: Internet pioneer Paul Baran
mike.a.sch...@gmail.com (Mike Schwab) writes: > Internet pioneer Paul Baran passes away, March 28, 2011. Designed > Packet switching that was incorporated into Arpanet in 1969 later IP. > http://www.bbc.co.uk/news/technology-12879908 > > After reading that, I found interesting this article, Celebrating 40 > years of the net , Oct 29, 2010. > http://news.bbc.co.uk/2/hi/technology/8331253.stm > > And I saw this article: Alan Turing designed the Ace computer, which > did computations while also keeping track of the accuracy, Feb 5, > 2011. > http://news.bbc.co.uk/2/hi/technology/8498826.stm note that the corporate internal network was larger than the arpanet/internet from just about the beginning until late '85 or early '86. http://www.garlic.com/~lynn/subnetwork.html#internalnet Big change came with the switch-over from host/IMPs on 1jan83 to tcp/ip ... and started to see workstations and PCs as network nodes (while communication group was severely restricting workstations and PCs to terminal emulation). misc. past posts mentioning efforts preserving terminal emulation paradigm http://www.garlic.com/~lynn/subnetwork.html#emulation At the time of the 1Jan83 switch-over ... arpanet/internet had something like 100 IMP network nodes with approx. 250 connected hosts. At that time, the internal network was approaching 1000 hosts/nodes reached a few months later. misc. old email mentioning internal network http://www.garlic.com/~lynn/lhwemail.html#vnet some of this discussed in (linkedin) Greater IBM group discussion about the NSFNET backbone: http://www.garlic.com/~lynn/2011d.html#65 IBM100 - Rise of the Internet http://www.garlic.com/~lynn/2011d.html#66 IBM100 - Rise of the Internet http://www.garlic.com/~lynn/2011e.html#6 IBM100 - Rise of the Internet -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: junking CKD; was "Social Security Confronts IT Obsolescence"
from long ago and far away, IBM Jargon: FS - n. Future System. A synonym for dreams that didn't come true. That project will be another FS. Note that FS is also the abbreviation for functionally stabilized, and, in Hebrew, means zero, or nothing. Also known as False Start, etc. ... snip ... I have a random signature setting that I periodically turn on ... randomly selects an entry from one of three randomly selected files ... IBMJARGON, 6670 sayings (file of quotations, we had modified the 6670 print driver to include random selection for output on the separator page), and zippy the pin head. -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: Downloading PoOps?
t...@cio.sc.gov (Bonno, Tuco) writes:
> Graduate, College of Conflict Management;
> University of SouthEast Asia;
> "I partied on the Ho Chi Minh Trail - tiến lên !! "
Friday PoOps trivia ... was one of the first mainstream IBM pubs to move
to cp67/cms script. The motivation was PoOps was a subset of the
internal architecture "redbook" (for the red 3ring binder that it was
distributed in). With cms script command line option, could print either
the full architecture "redbook" ... or just the subset PoOps sections.
other Friday trivia
http://www.garlic.com/~lynn/2011b.html#7
$2.5B "windfall" for IBM (something over $17B in today's dollars)
... would have significantly helped to cover the reported $1b spent on
the (failed) Future system effort.
I had sponsored Boyd's briefings at IBM ... and some of his biographies
mentioned him doing stint in charge of "spook base" and IBM's $2.5B
windfall. Longer item on "Boeing Plant 2" referencing helping with BCS
and IBM mainframes (only couple hundred million in renton datacenter)
about time Boyd was command "spook base"
http://www.garlic.com/~lynn/2010q.html#59
old item with lots of detail about spook base (including operation
having largest bldg in the region) ... gone 404 ... but lives on at
wayback machine:
http://web.archive.org/web/20030212092342/http://home.att.net/~c.jeppeson/igloo_white.html
above ("Other High Technology Assets") mentions 1130/2250s, 360/50,
360/65s & 2305s and cost(?) $1billion a year to operate.
2250M1 were direct mainframe channel attach ... as undergraduate at
univ. I had written driver to interface cp67/cms editor to 2250M1 on the
360/67. "2250M4" was the 1130/2250 combination (2250M1 & 2250M4 were
approx. same price).
2301 were fixed-head drum. it was similar to 2303 fixed-head drum
... but transferred data over four heads in parallel ... getting over
mbyte transfer rate ... and frequently found as paging devices on 360/67
(but had only 4mbyte capacity). Later 2305s (fixed head disk) with
12mbyte capacity, were common on 370. If NKP had 2305s, they would have
been some of the earliest.
Boyd would relate about frequently telling everybody about how it
wouldn't work (in part because other things had similar signatures).
other refs:
http://en.wikipedia.org/wiki/Nakhon_Phanom_Royal_Thai_Navy_Base
http://aircommandoman.tripod.com/
other refs to Boyd
http://www.garlic.com/~lynn/subboyd.html
--
virtualization experience starting Jan1968, online at home since Mar1970
--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO
Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: junking CKD; was "Social Security Confronts IT Obsolescence"
John Chase wrote: > Actually, it's "favorite son" operating system; as in "most favored" > or "takes precedence over all others" or "gets all the attention". > Might also be an oblique reference to the dead "Future System" that > was to be the "be all and end all" of operating systems. re: http://www.garlic.com/~lynn/2011e.html#45 junking CKD; was "Social Security Confronts IT Obsolescence" in the wake of FS demise ... there was mad rush to get stuff back into the 370 hardware & software product pipelines (there are claims that the distraction of FS allowed clone processors to gain market foothold) ... doing 303x (3031 was 158, 3032 was 168, 3033 started out 168 wiring/layout with faster chips) in parallel with 370/xa ... some discussion of FS, 303x, and 3081 http://www.jfsowa.com/computer/memo125.htm POK managed to convince corporate to kill vm370, shutdown the vm370 development group and move all the people to pok to support mvs/xa development (or otherwise mvs/xa wouldn't be able to meet ship schedule). Endicott managed to save vm370 product mission ... but had to reconstitute a development group from scratch. The shutdown strategy for the vm370 product group was to not inform them until the very last possible minute ... minimizing the number of people that might find something else. The information was leaked ... resulting in witch hunt to find the person responsible (extremely paranoid atmosphere in the bldg. during that period). There was joke about the head of POK was major contributor to vax/vms ... because so many of the development group went to work on vms. the MVM upthread historical reference: http://www.garlic.com/~lynn/2011d.html#73 has os/vs2 release 1 (SVS) plus delta for os/vs2 release 2 (MVS) on "glide path" to os/vs2 release 3 (FS). Also mentioned, simpson (from hasp, aka jes2) did RASP ... basically paged-mapped MFT. He then left, and was redoing RASP from scratch (in clean room), at Amdahl. as an aside ... one of the "nails" in the FS coffin was that if ACP (TPF) were run on FS machine built out of the fastest circuits then available (370/195) it would have the throughput of 370/145 ... 1/20 to 1/30 the thruput of eastern acp/SystemOne (on 370/195). misc. past posts mentioning ckd, fba, multi-track search http://www.garlic.com/~lynn/submain.html#dasd misc. past posts mentioning FS http://www.garlic.com/~lynn/submain.html#futuresys another FS reference: http://www.cs.clemson.edu/~mark/fs.html -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: junking CKD; was "Social Security Confronts IT Obsolescence"
bi...@mainstar.com (Bill Fairchild) writes: > It was. ECKD was announced in the early- to mid-80s, which was 25+ > years ago, which is several decades ago. Not all users respond > quickly. as expected ... they were using "eckd" ... and just not bothering to fully qualify ... since the transition occured so many decades ago ... it possibly appeared superfluous at this point for the distinction (unless in legacy discussion that specifically is about differences). past posts in thread: http://www.garlic.com/~lynn/2011e.html#31 "Social Security Confronts IT Obsolescence" http://www.garlic.com/~lynn/2011e.html#35 junking CKD; was "Social Security Confronts IT Obsolescence" http://www.garlic.com/~lynn/2011e.html#37 junking CKD; was "Social Security Confronts IT Obsolescence" http://www.garlic.com/~lynn/2011e.html#43 junking CKD; was "Social Security Confronts IT Obsolescence" http://www.garlic.com/~lynn/2011e.html#44 junking CKD; was "Social Security Confronts IT Obsolescence" http://www.garlic.com/~lynn/2011e.html#45 junking CKD; was "Social Security Confronts IT Obsolescence" -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: junking CKD; was "Social Security Confronts IT Obsolescence"
re: http://www.garlic.com/~lynn/2011e.html#31 "Social Security Confronts IT Obsolescence" http://www.garlic.com/~lynn/2011e.html#35 junking CKD; was "Social Security Confronts IT Obsolescence" http://www.garlic.com/~lynn/2011e.html#37 junking CKD; was "Social Security Confronts IT Obsolescence" http://www.garlic.com/~lynn/2011e.html#43 junking CKD; was "Social Security Confronts IT Obsolescence" http://www.garlic.com/~lynn/2011e.html#44 junking CKD; was "Social Security Confronts IT Obsolescence" there is also some possibility that the opposition to my providing FBA support was simply POK favorite son operating system campaign against me. after transferring to the west coast, they let me wander around and get into trouble. In the disk development and test labs (bldg. 14 & 15 on san jose plant site) ... they were doing stand-alone, dedicated time, around the clock, 7x24 scheduled testings. They mentioned that they had tried MVS ... hoping to do multiple concurrent testing in operating system enviornment ... but even with just a single 'testcell" (development device), MVS had 15min MTBF. I offerred to redo IOS to make it absolute bullet proof & never fail ... providing them with multiple concurrent, "on-demand" testing (significantly increasing development productivity since they now could test anytime they needed w/o having to wait for scheduled, dedicated time). I did an internal report on many of the items which happened to make passing reference to the MVS 15min MTBF. I was then called by somebody from the POK favorite son operating system ... and foolish me, I thot it was going to be about getting all the enhances incorporated, but they were bringing down their forces on my head ... wanting to know who my manager was ... and trying to make sure I never mentioned anything about them again (preferrably even no longer being an employee). Ferguson & Morris 1993 book describes that in the wake of FS failure, the corporate culture had been replaced with sycophancy and "make no waves" ... or in Boyd terms having to make a career choice between "To Be or To Do" ... from dedication of Boyd Hall at Air Force Weapons School, 17Sep1999 ... reference http://www.garlic.com/~lynn/2000e.html#35 This is discussed recently in (linkedin) former/current IBM group ... in IBM Jargon definition of "fast track" (sub)thread: http://www.garlic.com/~lynn/2011d.html#12 I actually miss working at IBM http://www.garlic.com/~lynn/2011d.html#13 I actually miss working at IBM http://www.garlic.com/~lynn/2011d.html#15 I actually miss working at IBM http://www.garlic.com/~lynn/2011d.html#16 I actually miss working at IBM http://www.garlic.com/~lynn/2011d.html#78 I actually miss working at IBM http://www.garlic.com/~lynn/2011e.html#7 I actually miss working at IBM http://www.garlic.com/~lynn/2011e.html#9 I actually miss working at IBM since they were already doing their worst ... it didn't matter later, related to 3380 ship (had been announced Jun80) ... I send email about standard collection of error tests (to be expected at customers) ... MVS was failing in all cases & in 2/3rds of the cases, there was no indication of what forced the re-ipl ... old email: http://www.garlic.com/~lynn/2007.html#email801015 misc. past posts getting to play disk engineer in bldgs 14&15 (which still exist at the plant site, although many others have been plowed under) http://www.garlic.com/~lynn/subtopic.html#disk ... footnote ... I had sponsored Boyd's briefings at IBM ... misc. past posts http://www.garlic.com/~lynn/subboyd.html -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: junking CKD; was "Social Security Confronts IT Obsolescence"
john.mck...@healthmarkets.com (McKown, John) writes: > Perhaps "not financially viable". "We" complain about how much z/OS > costs right now. Imagine the howls of rage if IBM were to increase the > cost of z/OS by 10% (to pick a round, random, number) and say that it > was to allow z/OS to use FBA devices. PDSes are a integral part of > z/OS (like it or not). Many people still dislike PDSEs. PDSs can't > exist without CKD. So to go "pure" FBA (to remove the dependency on > ECKD) would require a huge investment. Now, to add FBA support for > access methods which are inherently FBA compatible (VSAM et al.) would > likely be easier. as I've mentioned a number of times before ... long ago and far away the group told me that even if I provided them fully integrated and tested FBA support ... I still needed a $26M business case to cover training and documentation ... and I could only use incremental new sales in the business case (say $200M-$300M additional disk sales) ... and wasn't able to use life-cycle cost savings (that were enormous ... both for the company as well as customers ... totally dwarfing everything else). misc. past posts mentioning ckd, fba, multi-track search, etc http://www.garlic.com/~lynn/submain.html#dasd recent "MVM" thread ... from the definition in IBM Jargon as the original name for MVS, there was an enormous simulation layer added going from MVT to OS/VS2 ... basically, initially CCWTRANS was imported from CP67 (virtual machine vm370 percusor on 360/67)into EXCP processing which had to scan the passed channel program and build a duplicate with real addresses for execution. http://www.garlic.com/~lynn/2011d.html#71 Multiple Virtual Memory http://www.garlic.com/~lynn/2011d.html#72 Multiple Virtual Memory http://www.garlic.com/~lynn/2011d.html#73 Multiple Virtual Memory Now since all the "real" CKD disks have been FBA for a long time, then for decades, there has been a fairly large simulation layer (in the controller) that takes channel programs and perform emulated CKD function. There is roughly equivalent in various of the 370 simulators that run on intel & other platforms, with their own software layer simulating CKD function on FBA devices. So possible transition phase (decades ago) would have been to enhance official access methods to support native FBA ... ... and then include a multi-track search emulation layer in the EXCP channel program translation ... doing the same exact function currently performed in the lower layers, since *ALL* disks have been native *FBA* for some time (somebody has to be doing all that simulation). That would go a long way to accelerating weaning the dependency off multi-track search. -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: junking CKD; was "Social Security Confronts IT Obsolescence"
ps2...@yahoo.com (Ed Gould) writes: > Lyn: > > I bow to your expertize and have not read your paper on the 3725. > > My sort of well lets say home grown experience with trial and error (sigh a > lot > of errorr). > Gut instinct said the limiting factor was the byte channel (which I > understood) > was the vast majority of channel hook ups for the box. re: http://www.garlic.com/~lynn/2011e.html#31 "Social Security Confronts IT Obsolescence" http://www.garlic.com/~lynn/2011e.html#35 junking CKD; was "Social Security Confronts IT Obsolescence" http://www.garlic.com/~lynn/2011e.html#37 junking CKD; was "Social Security Confronts IT Obsolescence" you must have strayed from the archived ckd/eckd posts into archived sna/vtam misinformation thread (in a.f.c. newsgroup): http://www.garlic.com/~lynn/2011e.html#32 SNA/VTAM Misinformation http://www.garlic.com/~lynn/2011e.html#34 SNA/VTAM Misinformation the above also references more in (linkedin) "Greater IBM" group thread. note that in the above ... series/1 NCP emulation involved a channel interface board that attached to mainframe on same exact channel as 3725 and appeared to the mainframe exactly as a 3725 (slight of hand was that it told all the mainframes that resources were cross-domain ... "owned" by somebody else). Since the interface board and channel appeared identical ... then any related limitation was identical for 3725 and series/1. slight topic drift ... long ago and far away ... there was an internal effort to convince the communication group to use "peachtree" (processor for series/1) as being significantly more capable than the processor chosen for 37x5. additional topic drift ... even longer ago, as undergraduate in the 60s ... i added tty/ascii terminal support to cp67. cp67 had 1052 & 2741 support with fancy automatic terminal recognition ... fancy use of 2702 SAD command to re-associate different line-scanner to port. I then intergrated TTY/ASCII ... supporting automatic terminal identification (and re-associating different line-scanner with 2702 SAD command). It worked fine for leased line ... but i wanted to do single dial-up phone number (& hunt group) for all dial-up terminals ... where it broke. While 2702 allowed changing line-scanner on port ... 2702 took shortcut and hardwired oscillator/line-speed on each port. This was somewhat the motivation for the univ. to start clone controller project, reverse engineering mainframe channel interface, building mainframe channel board for interdata/3 and programming interdate/3 to simulate 2702 ... but also doing automatic line-speed operation. four of us get written up as being responsible for (some part of) clone controller business ... misc. past posts http://www.garlic.com/~lynn/subtopic.html#360pcm decade or so ago, was in large datacenter with a many generation descendent of that box handling large percentage of dial-up POS cardswipe terminals in the country ... claim was that the channel interface board hadn't changed ... although it was a many times descendent of interdate/3 (including name change when perkin/elmer bought interdata). -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: junking CKD; was "Social Security Confronts IT Obsolescence"
bi...@mainstar.com (Bill Fairchild) writes: > Lynn, > > I signed in to LinkedIn and was unable to find the reference, so > thanks for including the URL for the missing LinkedIn reference. I > read through that reference and saw 16 comments, only one of which > mentioned very bad throughput for CKD disks. No technical explanation > was given for the bad throughput; i.e., was it hardware limitations in > CKD, software limitations in Oracle, etc.? This comment was posted 23 > days ago, ca. 28 years after IBM first announced ECKD and > forward-thinking users began planning to junk their CKD by going to > ECKD. re: http://www.garlic.com/~lynn/2011e.html#31 "Social Security Confronts IT Obsolescence" http://www.garlic.com/~lynn/2011e.html#35 junking CKD; was "Social Security Confronts IT Obsolescence" I'm still waiting for followup ... it says zVM, zLinux and Oracle ... so presumably it is relatively current hardware, processors, disks, software, etc. The reference is that bad performance was rectified moving off CKD to some flavor of FBA (presumably some recent flavor of ECKD, lots of users may qualify CKD/FBA ... but I can understand lots of current users not bothering to make the CKD/ECKD distinction; I can't imagine any existing "z" mainframe with "real" pre-ECKD disks) That don't mention it as an age or legacy issue ... the zVM & zLinux aren't that old. There always is some possibility that zVM, zLinux, and/or current Oracle never bothered to optimize their (e)ckd support as well as they have FBA. pure conjecture ... a possible motivation for not bothering with fine-tuning any (e)ckd support is that these days all (e)ckd devices are really some form of FBA device with an additional eckd simulation layer on top. Given native FBA device support ... going directly to the native FBA device eliminates an extraneous eckd simulation layer (aka for any eckd device, an equivalent native FBA device could be used w/o the additional, unnecessary eckd layer). the ckd/eckd simulation layer continues to live on because MVS (& its descendants) have been unable to support the native devices. misc. past posts mentioning fba, ckd, multi-track search, etc http://www.garlic.com/~lynn/submain.html#dasd -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: junking CKD; was "Social Security Confronts IT Obsolescence"
bi...@mainstar.com (Bill Fairchild) writes: > It was. ECKD was announced in the early- to mid-80s, which was 25+ > years ago, which is several decades ago. Not all users respond > quickly. re: http://www.garlic.com/~lynn/2011e.html#31 "Social Security Confronts IT Obsolescence" oh, the missing linkedin URL reference: http://lnkd.in/ajGuA2 reference was to "CKD" disks didn't change ... controllers added some extra stuff (eckd) ... originally for "Calypso" ... the 3880 controller speed-matching buffer ... allowing 3380/3880 3mbyte connenction to (370/168 2880) 1.5mbyte channels ... which had enormous problems (that wouldn't/don't exist w/FBA). old email discussing calypso (eckd) and how bad the problems were (several severity ones in the field): http://www.garlic.com/~lynn/2007e.html#email820907b above also mentions the dismal prognosis of ever getting MVS to support FBA (I've periodically mentioned in the past about being told that even if I provided MVS with fully integrated & tested FBA support, I still needed $26M business case to cover education and pubs ... and I couldn't use lifecycle savings ... only incremental new sales). past posts with references to calypso/eckd: http://www.garlic.com/~lynn/2004o.html#7 Integer types for 128-bit addressing http://www.garlic.com/~lynn/2007e.html#40 FBA rant http://www.garlic.com/~lynn/2007f.html#0 FBA rant http://www.garlic.com/~lynn/2008q.html#40 TOPS-10 http://www.garlic.com/~lynn/2009k.html#44 Z/VM support for FBA devices was Re: z/OS support of HMC's 3270 emulation? http://www.garlic.com/~lynn/2009p.html#11 Secret Service plans IT reboot http://www.garlic.com/~lynn/2010e.html#36 What was old is new again (water chilled) http://www.garlic.com/~lynn/2010h.html#30 45 years of Mainframe http://www.garlic.com/~lynn/2010n.html#14 Mainframe Slang terms -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: "Social Security Confronts IT Obsolescence"
r.skoru...@bremultibank.com.pl (R.S.) writes:
> SSA? It's obsoleted by FC and SAS. Even IBM don't use SSA anymore.
> (sorry couldn't resist) ;-)
old post about 9333/Harrier (serial copper) turning into SSA. I had
been working on getting them to turn into FCS (fiber channel standard)
compatibility (at 1/8th or 1/4th 1gbit FCS standard, aka switch with
ports for serial fiber and serial copper)) ... but instead they decided
to do something that was non-interoperable with anything else.
http://www.garlic.com/~lynn/95.html#13 ssa, grump
of course some of the mainframe channel people then start showing up at
FCS standards meetings and doing unnatural things to the standard to
come up with FICON.
recent related posts in both (linked) "IBM Alumni" & "Greater IBM"
groups ("IBM Watson's Ancestors: A Look at Supercomputers of the Past"):
http://www.garlic.com/~lynn/2011d.html#7
http://www.garlic.com/~lynn/2011d.html#24
http://www.garlic.com/~lynn/2011d.html#29
http://www.garlic.com/~lynn/2011d.html#40
for other drift ... recent thread in (linkedin) Mainframe group about
Oracle on zLinux under zVM having bad thruput on "CKD" disks (before
moving to non-CKD) ... "CKD" should have been junked several decades
ago. misc past posts on the subject:
http://www.garlic.com/~lynn/submain.html#dasd
(sorry couldn't resist) ;-)
--
virtualization experience starting Jan1968, online at home since Mar1970
--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO
Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: Maybe off topic
ps2...@yahoo.com (Ed Gould) writes: > Thanks... > > My memory seemed too jump when I saw QBE... I think that was it. > THE BIG block letters on the screen were QBE. > > I do not know How I ever forgot those initials but I did. > Now onto QBE. Was it iBM code or an IUP or ... . A quick google says it > was > written by IBM. > > Ed re: http://www.garlic.com/~lynn/2011d.html#52 Maybe off topic http://www.garlic.com/~lynn/2011d.html#54 Maybe off topic http://www.garlic.com/~lynn/2011d.html#55 Maybe off topic "Shoot-out at the OK Corral" ... (between QBE & SQL): http://www.mcjones.org/System_R/SQL_Reunion_95/sqlr95-Shoot-ou.html from above (QBE being in the field as an IUP) And there were people in the field, and they loved it. They had stories of tape librarians who'd automated their tape library with it, and Gene Trivett was going around and fixing some of the performance problems, and it was popping up all over the planet. So it had a very loyal following. It was obvious to everybody that this did something wonderful. That this was an end-user program. So then the question became, "So why don't we cancel System R?" or "Why don't we grow this thing?" ... snip ... a little later on in above: I don't have the exact date, but around 1978, right? When did the actual shoot-out occur? 1978? Gomory asked Dick Case to do a review of the work. Dick Case included Ashok Chandra, who currently runs the Computer Science Department - he's the latest version of Frank King - and one other person, who were all disinterested people, but were technically capable. They went to Yorktown and learned all about QBE, and then they came to San Jose to learn all about System R, and I gave them my long lecture about how the lock manager works and how Compare-and-Swap could do locking, and we did it all right, and we knew how to do Compare-and-Swap-Double. Dick Case was really impressed, because he's probably the architect of Compare-and-Swap. ... snip ... as I've posted before, compare&swap was invented by charlie at the cambridge science center working on fine-grain multiprocessor locking for cp67 (compare-and-swap was chosen because "CAS" are charlie's initials). we tried to get "CAS" into 370, but were rebuffed because the POK favorite son operating system people claimed that test&set was more than adequate. The challenge given us by the owners of 370 architecture was to come up with uses other than kernel multiprocessing. Thus was born were the uses for application multithreaded operation, examples that still appear in principle of operations. misc. past posts mentioning multiprocessor support &/or compare&swap http://www.garlic.com/~lynn/subtopic.html#smp some more QBE in discussion about VS/QUERY (QMF): http://www.mcjones.org/System_R/SQL_Reunion_95/sqlr95-VS_QUERY.html for other topic drift: http://www.mcjones.org/System_R/SQL_Reunion_95/sqlr95-Prehisto.html above mentions a project at cambridge science center. one of the people working on the project was the "L" ... in "GML" which was invented at CSC in 1969. In the late '70s, "GML" morphs into ISO standard as "SGML" ... and then in the late '80s, "SGML" morphs into "HTML". misc. past posts mentioning gml, sgml, html, etc http://www.garlic.com/~lynn/submain.html#sgml "L" transfers from CSC to SJR ... shortly after I did. misc. past posts mentioning cambridge science center, 4th flr, 545 tech sq http://www.garlic.com/~lynn/subtopic.html#545tech -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: Maybe off topic
hmerr...@jackhenry.com (Hal Merritt) writes: > I seem to recall working on a product called SLR (Service Level > Reporter). My (very poor) memory is of databases that looked a lot > like those later introduced by DB2. re: http://www.garlic.com/~lynn/~lynn/2011d.html#52 Maybe off topic http://www.garlic.com/~lynn/~lynn/2011d.html#54 Maybe off topic dating back before sql (originally on vm370) were some 4th generation languages that were offered by virtual machine based commercial service bureaus (initially late 60s, cp67 and later vm370) ... RAMIS, NOMAD, FOCUS (in some cases developed as part of competition between different virtual machine based commercial service bureaus) RAMIS wiki page http://en.wikipedia.org/wiki/Ramis_Software NOMAD wiki page http://en.wikipedia.org/wiki/Nomad_software FOCUS wiki page http://en.wikipedia.org/wiki/FOCUS RAMIS and NOMAD reference at computer history museum http://www.computerhistory.org/collections/accession/102658182 Computer History Museum PDF file: http://archive.computerhistory.org/resources/text/Oral_History/RAMIS_and_NOMAD/RAMIS_and_NOMAD.National_CSS.oral_history.2005.102658182.pdf RAMIS & FOCUS ... brief history of 4th gen languages: http://ibmmainframes.com/about5018.html The Wholly Unofficial NOMAD Website http://www.decosta.com/Nomad/ also in the time-frame of SQL/RDBMS being done at SJR (research on the west coast) there was query-by-example being done at YKT (research on the east coast) ... old email about QBE presentation at SJR (by "Father of QBE, Arch-enemy of System R"): http://www.garlic.com/~lynn/2002e.html#email800310 in this old post http://www.garlic.com/~lynn/2002e.html#44 SQL wildcard origins? QBE wiki http://en.wikipedia.org/wiki/Query_by_Example then there is this on "pre-history" (also from the 95 reunion): http://www.mcjones.org/System_R/SQL_Reunion_95/sqlr95-Prehisto.html Ingres has gone thru multiple incarnations ... we worked with them in the 90s as part of our high-availability, cluster operation http://en.wikipedia.org/wiki/Ingres_%28database%29 in conjunction with HA/CMP product: http://publib.boulder.ibm.com/infocenter/clresctr/vxrx/topic/com.ibm.cluster.hacmp.doc/hacmpbooks.html past posts http://www.garlic.com/~lynn/subtopic.html#hacmp mention that original INGRES language was QUEL http://www.mcjones.org/System_R/SQL_Reunion_95/sqlr95-Teradata.html above also mentions that a spinoff from INGRES project was Britton-Lee ... including Bob Epstien as CTO. When Bob left for Teradata (and then later founded Sybase), there was lots of recruiting going on around bldg28/SJR (usually across the street from the plant site) for replacement for Bob. Of course not nearly on the scale of Shugart recruiting disk engineers http://www.businessweek.com/1997/34/trans34/shugart.htm http://www.mdhc.scu.edu/100th/Progress/Shugart/shugart.html Sybase wiki ... we also worked with in porting to HA/CMP cluster mode: http://en.wikipedia.org/wiki/Sybase Above mentions Sybase had a deal with Microsoft to remarket as "SQL Server" (... until version 4.9, Sybase and Microsoft SQL Server were virtually identical) Oracle wiki page (started out as "SDL", Oracel name came from CIA-funded project that Ellison had worked on at Ampex) ... we also worked with (RDBMS) Oracle http://en.wikipedia.org/wiki/Oracle_Database as referenced in this post about old Jan92 meeting in Ellison's conference room http://www.garlic.com/~lynn/95.html#13 Oracle wiki mentions it was the first commercially available SQL-based RDBMS (1979) ... as opposed to first commercial RDBMS (Multics 1976). http://www.mcjones.org/System_R/mrds.htm The other major RDBMS player from the period (that we worked with in HA/CMP) was Informix (before IBM bought them) http://en.wikipedia.org/wiki/IBM_Informix DB2 was rather late RDBMS to ship ... largely because EAGLE was the MVS strategic DBMS ... and it wasn't only after EAGLE effort crashed was there the rush to get System/R (and SQL/DS) over to MVS for DB2. DB2 announced 7Jun1983, avail. 2Apr1985 http://en.wikipedia.org/wiki/IBM_DB2 note that in 1989 ... there was work on totally different DB2 ... targeted for OS2. past posts mentioning System/R http://www.garlic.com/~lynn/subtopic.html#systemr also past posts getting to play disk engineer in bldgs14&15 http://www.garlic.com/~lynn/subtopic.html#disk -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: Maybe off topic
l...@garlic.com (Anne & Lynn Wheeler) writes: > System/R reunion discussion of SQL/DS mentions that massive EAGLE > project in STL kept attention away from RDBMS ... allowing System/R to > get out as SQL/DS > http://www.mcjones.org/System_R/SQL_Reunion_95/sqlr95-SQL_DS.html > > quote from above: > > The surprise of the MVS project was that it happened faster than I > thought it would. In other words, Plan A collapsed, all right? Eagle > collapsed, and all of a sudden, everyone turned to us and said, "OK, > when can you ship this database product?" [laughter] And that's when > we had to make some fairly hasty, difficult decisions on ... > > ... snip ... re: http://www.garlic.com/~lynn/2011d.htmL#52 Maybe off topic more on crash of Eagle ... and question about how fast a system/r could be released on MVS (aka DB2) http://www.mcjones.org/System_R/SQL_Reunion_95/sqlr95-DB2.html above mentions that marketing quy was looking at a poster for the original Santa Teresa lab announcement ... with an eagle soaring above the building ... and decided on EAGLE for the grand MVS DBMS effort. I was in DC with offspring for vacation the week before the Air & Space museum opened (*AND* also the week before STL was to be opened). At that time, STL was going to be called Coyote lab (the closest post office and the name of the valley). That week a working ladies organization called "Coyote" was demonstrating on the steps of the capital (and getting lots of press) ... which appeared to prompt quick revision of the lab's name from Coyote to Santa Teresa (nearby cross-road, lab has since been rename Silicon Valley lab). -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: Maybe off topic
ps2...@yahoo.com (Ed Gould) writes: > I was reading some article today about IBM & DB2 today. I think it > said something like DB2 was IBM's real first try into relational > databases. My memory is foggy here something in the back of my mind > says that is not quite correct. Back in the 70's (?) I vaguely > remember IBM having a FDP(?) that claimed to do relational database. > By slim memory says it may have been VM based. I do remember it had a > 4 page white sales type paper(IUP?). No name comes up. Can anyone > supply me with a product name? I do recall something like this as we > were looking at a product and the show stopper was that it needed VM. system/r ... san jose research, bldg. 28. work was for vm/cms on the group's 370/145. there was then technology transfer to endicott for sql/ds product for vm, vs1 & dos/vs. some past posts about system/r http://www.garlic.com/~lynn/submain.html#systemr when "eagle" effort "crashed" in STL, the system/r group was asked how fast they could turn out something for MVS. System/R reunion discussion of SQL/DS mentions that massive EAGLE project in STL kept attention away from RDBMS ... allowing System/R to get out as SQL/DS http://www.mcjones.org/System_R/SQL_Reunion_95/sqlr95-SQL_DS.html quote from above: The surprise of the MVS project was that it happened faster than I thought it would. In other words, Plan A collapsed, all right? Eagle collapsed, and all of a sudden, everyone turned to us and said, "OK, when can you ship this database product?" [laughter] And that's when we had to make some fairly hasty, difficult decisions on ... ... snip ... lots more in the System/R 1995 reunion http://www.mcjones.org/System_R some mention in Jim's departing "MIP Envy": http://www.garlic.com/~lynn/2007d.html#email800920 slightly later 24sep80 version here: http://research.microsoft.com/~gray/papers/CritiqueOfIBM%27sCSResearch.doc Oracle executive mentioned in this Jan1992 meeting claimed (when he was at STL) to have handled the SQL/DS tech. transfer from Endicott back to STL for DB2 http://www.garlic.com/~lynn/95.html#13 past posts about Jim palming off bunch of stuff on me when he was departing for Tandem ... including consulting with the IMS group and customers running System/R http://www.garlic.com/~lynn/2007.html#email801006 http://www.garlic.com/~lynn/2007.html#email801016 some also discussed at celebration held for Jim at Berkeley http://www.garlic.com/~lynn/2008i.html#32 A Tribute to Jim Gray: Sometimes Nice Guys Do Finish First audio from the celebration http://www.garlic.com/~lynn/2008i.html#50 Microsoft versus Digital Equipment Corporation sql/ds mentioned here ... http://en.wikipedia.org/wiki/IBM_SQL/DS sql/ds redbook http://www.redbooks.ibm.com/abstracts/gg244047.html and sql/ds "rebranded" here http://www-01.ibm.com/software/data/db2/vse-vm/ as referenced above ... the "official" DBMS effort in STL was called "EAGLE", but when that crashed ... then the system/r group was asked how fast could a RDBMS be turned out for MVS. recent post/mention in (linkedin) Greater IBM http://www.garlic.com/~lynn/2011d.html#42 Mainframe Hall of Frame. List of influential mainframers thoughout history as an aside ... the first commercial offering of Codd's relational (worked at research in bldg. 28) http://en.wikipedia.org/wiki/Edgar_F._Codd was on Multics http://en.wikipedia.org/wiki/Multics_Relational_Data_Store more on MRDS from the System/R reunion: http://www.mcjones.org/System_R/mrds.html RDBMS wiki page http://en.wikipedia.org/wiki/Relational_database_management_system trivia ... multics was on 5th flr of 545 tech sq. The science center that did virtual machines, cp67/cms, etc ... was on 4th flr of 545 tech sq. When the cp67 group split off from the science center, they took over the Boston Programming Center on the 3rd flr (morphing into the vm370 development group). The development group outgrew the space on the 3rd flr and moved out to the old SBC bldg. (vacated in the legal actions where IBM transferred SBC to CDC) in Burlington Mall. misc. past posts mentioning 545 tech. sq http://www.garlic.com/~lynn/subtopic.html#545tech in the wake of demise of Future System project ... misc. past posts http://www.garlic.com/~lynn/submain.html#futuresys there was mad rush to get products back into the 370 (hardware & software) product pipeline ... having been killed off during the FS period. Part of that was the head of POK managed to convince the corporation to kill-off VM370 Burlington Mall development group, becuase he needed to transfer all the people to POK for MVS/XA development (or otherwise he couldn't meet the ship schedule). Endicott managed to save the vm370 product mission, but had to recreate a development group from scratch. -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, sen
Re: z/OS 1.13 preview
ps2...@yahoo.com (Ed Gould) writes: > I cannot remember where my first run in with VSE was. It was a LONG > time ago. Probably im the mid 70's (???). I think it was in St Louis > at an IBM school there.We were trying to set up a 4331 for our New > York Office. It was either there or out in the LA IBM office. All I > can remember is that I did not like it in general. It was not > consistant on how it handled "things" (control cards and the like) its > been so long that the abiortion must have reconcieved. I dio remember > thinking IBM was out of their gourd for propegatting it and it shouuld > have been put on suicide watch (I would have helped pull ther > trigger). ... 79?, maybe later ... mid-70s was 138/148 ... follow-on to 135/145 ... still vs1 & dos/vs in the failure of future system project ... there was mad rush to get stuff back into the 370 product pipeline (most activity had been killed off during the future system period) htpt://www.garlic.com/~lynn/submain.html#futuresys high-end did 303x ... 3031 & 3032 were repackaged 158 & 168 ... and 3033 started out with 168 wiring diagram map to chips that were 20% faster. chips also had ten times as many circuits ... initially mostly unused ... but during the product development some redesign to use the additional circuits got 3033 up to 1.5 times 168 (instead of 1.2 times). In parallel with 303x ... things started on "XA" ... for awhile known as "811" for nov78 date on many of the documents ... which eventually resulted in 3081. some discussion of both FS & 3081: http://www.jfsowa.com/computer/memo125.htm some of the benchmarks were being done on the engineering 4341 in the disk product test labs for the endicott performance test group ... since i seemed to have better access to (endicott) 4341 than they did. and with the failure of FS, mid-range started work on "E" architecutre ... and in 79 came out with 43xx machines (followon to 138 & 148) that supported both vanilla 370 and "E" (somewhat akin to 3081 with 370 & "XA" modes). misc. past 43xx email ... starting in jan79 doing benchmarks on engineering 4341s: http://www.garlic.com/~lynn/lhwemail.html#43xx "E" architecture was somewhat akin to initial VS2 (SVS) with much of the single virtual address space moved into microcode/hardware. 4341 announced 30Jan1979: http://www-03.ibm.com/ibm/history/exhibits/mainframe/mainframe_PP4341.html the above mentions 4341 supported 3370 ... which was the mid-range disk ... and was FBA. There was no mid-range CKD at the time ... which sort of left MVS out of the big explosion in the mid-range market ... could upgrade 370 and continue to use existing legacy DASD ... but was difficult to see MVS on all the 43xx that were starting to proliferate all over corporations in departmental conference rooms and supply rooms. Eventually 3375 was produced which was CKD emulated on 3370 FBA ... to address the lack of MVS support for FBA. misc. past posts mentioning FBA & CKD http://www.garlic.com/~lynn/submain.html#dasd -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: IBM 100: System 360 From Computers to Computer Systems
Allodoxaphobia writes: > There are a number of anecdotal stories about companies taking the > covers off and sending them to a paint shop to achieve their own > corporate color scheme. the science center had five 2314 8drive strings and one 2314 5drive string ... connected to the 360/67 (running cp67) ... and the IBM CE painted each a different color ... to help with tracking which one was which (for things like mount requests). misc. past posts mentioning science center http://www.garlic.com/~lynn/subtopic.html#545tech -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: Custom programmability for 3270 emulators
charl...@mcn.org (Charles Mills) writes: > Last one that I wrote was in about 1990. Anyone remember SNA? > > There are several 3270 vendors around. Some of the emulators have a macro > capability. internal parasite/story predated ibm/pc and relied on vm370 psuedo device and "passthru virtual machine" (do remote 3270 emulation over the internal network). old posts with description and some example stories ... including automated login to FE Retain system and retrieve PUT buckets: http://www.garlic.com/~lynn/2001k.html#35 http://www.garlic.com/~lynn/2001k.html#36 -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: Long-running jobs, PDS, and DISP=SHR
shmuel+ibm-m...@patriot.net (Shmuel Metz , Seymour J.) writes: > No. None of his scenarios involved concurrent updates. The danger > comes from scenarios other than the ones he presented. Of course, the > ABEND S213 will prevent corruption of the directory in that case. for a long time, CKD disks had a corrupted data vulnerability involving loss of power ... particular nasty when updating VTOC &/or PDF directories (which started to disappear with CKD being emulated on FBA ... since FBA tended to have countermeasures for the problems, in part because of predictable block sizes). The issue was if power was lost in the middle of write operation ... the channel/controller could continue to transfer data ... basically filling in with zeros (data was no longer coming from processor memory). The disk write could complete ... with the propogated zeros and correct error correcting (ECC) information written (based on the propogated zeros). On restoration of power ... there would be no disk error reading the record ... just that record would be all zeros from the point power was lost. -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: Testing hardware RESERVE
paulgboul...@aim.com (Paul Gilmartin) writes: > Long ago, circa MVS 3.8 without GRS, in our little lab we got > sporadic deadlocks when one job allocated SYSLIB on VOL001, > SYSLMOD on VOL002, and another allocated SYSLIB on VOL002, > SYSLMOD on VOL001. long ago and far away ... discussion of the ACP RPQ for 3830 ... allowing for fine granualarity locks (more like VAX/VMS) in lieu of reserve/release http://www.garlic.com/~lynn/2008i.html#email800325 in this post http://www.garlic.com/~lynn/2008i.html#39 American Airlines above references System/R which was the original relational/SQL done in bldg. 28 http://www.garlic.com/~lynn/submain.html#systemr Another approach ... is a CKD channel program with "compare&swap" semantics that was developed for HONE in the late 70s (US operation was possibly largest single-system-image, loosely-coupled operation in the world at the time) ... was more efficient than RESERVE/RELEASE (but not as efficient as ACP RPQ) ... since it involved additional rotation. At one-time there was extensive discussions with the JES2 multi-spool group doing something similar. Misc. past posts mentioning internal HONE system http://www.garlic.com/~lynn/subtopic.html#hone Later I needed a inverse of RESERVE for large cluster operation ... in recovery operation needing to remove a specific processor from the configuration ... I wanted a FCS switch operation to allow everybody ... but the processor that has been removed from the configuration (there is a failure mode where a processor stops, appears to have failed, and then later resumes ... potentially just before doing some I/O operation with global impact, aka it doesn't realize that it has been removed from the configuration). One of the problems was that FCS was being quite distracted with the complex effort to layer FICON on top of it (somewhat in the manner that *ALL* current day CKD is done by simulation on top of underlying FBA). -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: digitize old hardcopy manuals
afg0...@videotron.ca (Andreas F. Geissbuehler) writes: > I believe you once posted / answered a post about digitizing old hardcopy > manuals. I have some 30 volumes 1980..1995 vintage, about 8'000 B&W pages to > convert to PDF. bitsavers is somewhat ad-hoc ... although they do have software that turns scanning resulting in one file/page into multi-page file ... aka reference to having used it for old SHARE LSRAD report (done with multi-function (scanner, fax, printer): http://www.garlic.com/~lynn/2009.html#47 Bitsaver with discussion of some scanners & software: http://www.bitsavers.org/ IBM PDF section on bitsavers http://www.bitsavers.org/pdf/ibm/ wayback machine (archive.org) also does a lot of scanning http://www.archive.org/details/partnerdocs past post mentioning spring 2009 being asked to do something with the scan of Percora Hearings (30s congressional hearings into the crash and depression) online at archive.org (and scanned at Boston Public Library the previous fall), also trying to improve on the OCR http://www.garlic.com/~lynn/2009b.html#58 OCR scans of old documents using google's tesseract: http://code.google.com/p/tesseract-ocr/ wiki page ... mentioning large scale scanning programs at project gutenberg, google book search, open content alliance internet archive, amazon http://en.wikipedia.org/wiki/Book_scanning DIY book scanner (from wiki article) http://hardware.slashdot.org/story/09/12/13/1747201/The-DIY-Book-Scanner http://www.wired.com/gadgetlab/2009/12/diy-book-scanner/ off-the-wall artcile: http://www.labnol.org/internet/favorites/google-book-scanning-facilities-found/393/ -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: Date representations: Y2k revisited
frank.swarbr...@efirstbank.com (Frank Swarbrick) writes: > Or COBOL! Or Pascal. there are large number of characteristics of C language that result in programmers tending to shoot themselves in the foot ... that are not there in other languages. the original mainframe tcp/ip implementation had been done in vs/pascal ... and had none of the buffer-length related exploits (related to buffers and buffer indexing) that have been prevelent in C-language based implementations (it is almost as hard to shoot yourself in the foot with pascal as it is to not shoot yourself with C). of course there were other issues in that original vs/pascal tcp/ip implementation ... getting something like 44kbytes/sec aggregate using loads of processor. I did do the rfc1044 enhancements ... and in some tuning tests at cray research ... got channel speed (1mbyte/sec) thruput on 4341 using only small amount of processor (something like 500 times reduction in instructions executed per byte transferred). misc. past posts http://www.garlic.com/~lynn/subnetwork.html#1044 -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
Re: subscripti ng
popular press has people using less than 5% of their brains. there has been extensive advances in knowledge of the brain over the last decade from MRI studies. recent book discussing structure in some detail (also available on kindle) http://www.amazon.com/Iconoclast-Neuroscientist-Reveals-Think-Differently/dp/1422115011 a common theme in the book and various related papers on MRI studies is that as the brain grows and adapts, it attempts to optimize/minimize its energy (and oxygen) use ... apparently a survival characteristic (with the brain being one of the body's major energy user). -- virtualization experience starting Jan1968, online at home since Mar1970 -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
